Skip to content
CAI
Software that uses CAICheck a score

marcoemrich/agentic_coding_lab

43.7

Weak · 17 November 2026

355.2k

lines of production code

TypeScript

with JavaScript, Rust

1

measurement over time

CAI band scale
CAI lens gauges

What this system is

Behavioural changes

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 10 files: “data(runs): five GPT-6 Astra runs on game-of-life”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 10 files: “data(runs): six game-of-life smoke runs for the RQ-1.19 repair arms”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 10 files: “data: RQ-5 erweitert um v6-hybrid + TDD-Disziplin-Banden (F-5.6 neu)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 10 files: “feat(RQ-cc-vs-pi): Opus CC vs pi, thinking × no-thinking, n=5×4”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 103 files: “analyze-run: aggregate clean\_code metrics across all impl files”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 107 files: “data(rq): 20 Runs RQ-4.6 (Sol-Linie vs. v-Linie auf Opus/CC) + Reanalyse”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 107 files: “feat(RQ-workflow-reduction-opus5): 40 Runs auf sphinx + game-of-life — Kette ordnet nicht monoton”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 115 files: “Fill RQ-workflow-axis-gpt61-sol and record its findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 117 files: “Validate PTDD test-list dimensions across Opus and SOL”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 12 files: “research(RQ-model-quality): add opus-4-8 cells (n=3 each) on game-of-life × v4”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 13 files: “Fill the Opus gap cells and update four RQs' findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 13 files: “data(RQ-prompt-correctness): Opus-4.7-Datenlücke schließen + Reanalyse (93→128 Runs)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 14 files: “Add first-party EXACT TCR results to RQ-1.7”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 140 files: “Ship the project templates with the export and add the Rust template”.

(repo-wide) · low confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 143 files: “Answer RQ-exact-coding-python: the method's benefit is narrower than Java suggested”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 148 files: “Run Opus 5 Requesty TCR comparison”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 149 files: “Evaluate domain boundary and APP variants for SOL TCR”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 15 files: “Re-set up the TDD workflow comparison on the phase chain”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 15 files: “data(RQ-model-novel-pi): opus-5-requesty-Arme gefüllt, RQ komplett (18/18)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 15 files: “research(RQ-1.12): v6.5-end-refactor — iterativer Whole-src-Pass nach TDD-Loops”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 15 files: “research(RQ-model-novel-oc): fill GLM 5.1 cell × n=5 + findings update”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 152 files: “feat(RQ-architecture-axis-opus5): 50 Runs + Findings — Architektur-Achse haelt auf Opus 5”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 155 files: “chore: Stand-Festklopfer — RQ-4b, RQ-21, v4.1, v4.2-Sackgasse, Tooling”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 16 files: “Compare TCR with a parity Predictive TDD port”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 16 files: “data(pi): SOL-Routenvergleich Requesty vs OpenAI-Subscription, 8 Runs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 161 files: “feat(pi): v6.2.1-phase-continuation-pi + RQ-model-quality-pi/novel-pi auf n=5”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 162 files: “data: RQ-2 runs (45 GOL-CLI) + RQ-1 Opus-4-7 runs + cleanup deleted runs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 17 files: “data(runs): complete the five v6.1.5 power-fill runs committed mid-flight”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 18 files: “Add native Opus PTDD comparison RQ”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 18 files: “data(pi): SOL-Routenvergleich auf sphinx-score — Geltungsbereich eingeschraenkt”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 18 files: “feat(RQ-tdd-quality): v8a/v8b + claim-office hinzu, n=5, neue Findings F-8/F-9 + Empfehlung”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 18 files: “research(RQ-1.1-model-quality-oc): add DeepSeek V4 flash + pro cells (n=5 each)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 18 files: “research(RQ-1.11): v6.4 metric-driven-refactor — deterministic ESLint/McCabe pre/post”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 180 files: “Fill RQ-current-models-ptdd to 9 cells, drop Mistral, guard against empty runs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 19 files: “Add RQ-old-vs-new-exact-line-opus55 and fill its two retired-line cells”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 19 files: “research(RQ-model-novel): fill opus-4-8 cell (n=5) on claim-office × v4”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 19 files: “research(RQ-model-novel-oc): fill mistral-medium-3-5 × n=5 + cc-workspace setup + reanalyze”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 196 files: “Complete RQ-exact-coding-java with the refactor-subagent arm”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 20 files: “Fill the last gaps of RQ-prompt-correctness, RQ-model-novel, RQ-workflow-model”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 20 files: “data(RQ-model-quality-cursor): composer+grok gefuellt (10 Runs), opus offen”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 20 files: “feat(rq-1.1/1.2): PEP- und Emoji-Effekt auf v6.1-Basis”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 20 files: “feat(rq-1.7): Cross-Kata-Validierung v6.2 vs v6.1-with-why auf game-of-life”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 20 files: “research(RQ-1.14): v6.5-end-refactor auf game-of-life validiert → globale Quality-Baseline”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 21 files: “runs: add 22 RQ-3/RQ-4 runs from 2026-05-10”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 22 files: “RQ-4: aggregate 17 fill-runs, revise findings F-4.1/2/4 + add F-4.5/6”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 22 files: “data(rq): RQ-fable-vs-opus5 extended by Sonnet 5 -- the workflow does not close the tier gap”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 23 files: “feat(RQ-architecture-axis-sol-pi): v6.6-Zelle gefüllt, F-1.11 zur Metrik-Lücke”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 230 files: “data(runs): RQ-model-novel-pi 15 Zellen × n=5 (claim-office-example-mapping, v6.2-with-why-cleaned-pi)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 25 files: “experiment: measure forced Ponytail on SOL pi”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 25 files: “feat(workflows): v6.1.5 re-derives the lab split as a pure partition of v6.1”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 25 files: “feat: v6-hybrid workflow + RQ-7 (Workflow-Tradeoff-Hybrid)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 25 files: “refactor(workflows): rename v6.2-refactor-vocab → v6.2.1-refactor-vocab + archive”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 25 files: “research(RQ-harness): add CC/OC/pi v6.2 example-mapping runs + harness findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 259 files: “Add Java EXACT Coding workflow comparison”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 26 files: “Fill qwen3-8-flash-next: the cheap tier loses nothing on this kata”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 26 files: “data(RQ-architecture-axis-sol-pi): Baselines v1/v3 ergänzt, RQ auf 50 Runs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 27 files: “Wire Gemini 4 Argon and Mistral Large 4, smoke RQ-current-models-ptdd”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 27 files: “data(RQ-model-quality,RQ-model-novel): Opus 5 nativ ergänzt (game-of-life n=3, claim-office n=5)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 27 files: “feat(RQ-19, RQ-3b): cross-model correctness triage + model-effect on novel kata”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 28 files: “data(RQ-model-quality-pi): opus-5-requesty-Zelle gefüllt, RQ komplett (12/12)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 28 files: “data: RQ-6 Cross-Kata-Replikation auf claim-office; H2 falsifiziert”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 29 files: “data(RQ 2.1+2.2): Fable 5 ergänzt (model registry, CLI 2.1.170, Runs, Findings)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 29 files: “feat(kata-dev): RQ 1.3 Workflow-Sensitivitaet — 7 Runs + findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 30 files: “data(pi): K3-Zellen auf sference neu erhoben, Drop-Runs ersetzt”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 30 files: “docs(RQ-19, RQ-3b): Workflow×Modell-Interaktion + v6-hybrid opus-4-6 bereinigt”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 30 files: “feat(rq): GPT-5.3 Codex Spark verdrahten + RQ-spark-vs-sol, n=5 je Zelle”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 30 files: “research(RQ-model-novel-oc): fill DeepSeek V4 flash + pro cells (n=5 each)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 31 files: “research(RQ-1.13): game-of-life als 2. Kata (n=5×3 Workflows, opus-4-8)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 32 files: “runs: 34 experiment runs for RQ-9, RQ-9.1, RQ-10”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 33 files: “Add completed Opus 5 and Fable 5.1 runs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 36 files: “runs: check in 137 historical run dirs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 38 files: “Add native Opus 5 Base TDD runs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 38 files: “feat(rq-1.5): Why-Block-Effekt auf v6.1-Basis + neue Workflows v6.1-with-why und v6.2”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 40 files: “research(RQ-model-quality-oc): swap minimax→glm, fill 4 cells × n=5 + findings with cost”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 42 files: “research(RQ-1.13): v6.5-end-refactor auf opus-4-8 validiert (claim-office)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 43 files: “data(RQ-harness-requesty): Cross-Harness-Batch CC/OC/pi opus-4-8 (Requesty), n=5×6”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 45 files: “Fill the minimax and Java gap cells”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 45 files: “feat(research): RQ 4.1/4.2/4.3 Refill + findings + v6.1 in RQ-context”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 46 files: “Fill RQ-ptdd-verification-split and record its findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 48 files: “Rebuild the OpenCode DeepSeek cells on Requesty runs only”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 48 files: “research(RQ-model-novel-oc): fill 4 cells × n=5 + findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 50 files: “feat: v7-hybrid-green-refactor Workflow + F-7.6”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 51 files: “batch-plans: clean slate after v4 predictions patch”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 51 files: “data(runs): RQ-1.19 fill plus a period recheck of the v6.1 reference”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 51 files: “feat(rq): RQ-native-sol-workflows-sub — native Sol-Linie vs v3-Boden, n=5”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 54 files: “feat(rq-1.8/1.9): v6.3-audit-bundle workflow + Cross-Kata-Validierung GoL vs claim-office”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 55 files: “Answer RQ-gpt6-sol-vs-gpt56-sol, and find a blind spot in the mutation stage”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 568 files: “Re-measure three Opus 5.5 RQs on the phase chain”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 60 files: “feat(rq): RQ-1.18 -- APP-Subordination und Mess-Gradient auf der Sol-Linie”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 62 files: “data(rq): Runs und Auswertungen zu RQ-1.16 und RQ-1.17”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 62 files: “data: RQ-5 50 Runs (n=10 pro Workflow) + Subsampling-Analyse + Findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 62 files: “feat(rq-1.2/1.3/1.4): Emoji-Effekt + Pep×Emoji-Interaktion + Kata-Stresstest”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 66 files: “data(rq): RQ-astra-native-sol filled -- the native Sol line transfers”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 66 files: “data: RQ-3 + RQ-4 komplett neu erhoben unter explizitem API-Vertrag”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 69 files: “Open the workflow axis on GPT-6 Sol, and find the subagent arm does not replicate”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 70 files: “Evaluate isolated refactoring in PTDD v1”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 71 files: “research: validate stack profile extraction”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 73 files: “runs(rq-4.7, rq-1.19): 14-run union fill on opus-5-no-thinking”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 75 files: “Promote universal versioned PTDD workflow”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 77 files: “data(RQ-architecture-axis-sol-pi): 30 Runs, Findings F-1.1–F-1.5, RQ geschlossen”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 8 files: “data(rq): RQ-route-effect-pi n=5 in allen drei Zellen — Reasoning entlastet”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 8 files: “research(RQ-1.14): v6.4-per-cycle als 3. Zelle auf game-of-life (n=5)”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 84 files: “feat(kata-dev): RQ 1.2 Sphinx-Prompt-Sensitivitaet — 24 Runs + Findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 93 files: “Add TCR variant research workflows and SOL results”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 97 files: “Fill RQ-exact-coding-rust and record its findings”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 1 commit, 98 files: “data: RQ-4 erweitert um claim-office, n=5-10, mutation\_score auf alle grünen Runs”.

(repo-wide) · medium confidence · unverified

1 commit (0 fixes) modifying experiments/docker/rust.cache, experiments/stacks/rust-cargo

A change to existing behaviour in experiments/docker/rust.cache, experiments/stacks/rust-cargo — 1 commit, 3 files: “Add the rust-cargo stack”.

experiments/docker/rust.cache, experiments/stacks/rust-cargo · low confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-05-13\_00-04-43\_claim-office-user-story\_v5-exact-single-context\_opus-4-7, experiments/runs/2026-05-13\_00-08-19\_claim-office-user-story\_v5-exact-single-context\_opus-4-7, experiments/runs/2026-05-13\_00-19-33\_claim-office-user-story\_v5-exact-single-context\_opus-4-7-no-thinking

A change to existing behaviour in experiments/runs/2026-05-13\_00-04-43\_claim-office-user-story\_v5-exact-single-context\_opus-4-7, experiments/runs/2026-05-13\_00-08-19\_claim-office-user-story\_v5-exact-single-context\_opus-4-7, experiments/runs/2026-05-13\_00-19-33\_claim-office-user-story\_v5-exact-single-context\_opus-4-7-no-thinking — 1 commit, 9 files: “data: add 5 RQ-1 claim-office runs (Opus-4-7 + Opus-4-7-no-thinking user-story)”.

_experiments/runs/2026-05-13\_00-04-43\_claim-office-user-story\_v5-exact-single-context\_opus-4-7, experiments/runs/2026-05-13\_00-08-19\_claim-office-user-story\_v5-exact-single-context\_opus-4-7, experiments/runs/2026-05-13\_00-19-33\_claim-office-user-story\_v5-exact-single-context\opus-4-7-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-05-16\_09-44-03\_game-of-life-example-mapping\_v6-hybrid\_sonnet-4-6-no-thinking, experiments/runs/2026-05-16\_09-53-20\_game-of-life-example-mapping\_v6-hybrid\_sonnet-4-6-no-thinking, experiments/runs/2026-05-16\_10-41-18\_game-of-life-example-mapping\_v6-hybrid\_opus-4-6-portkey-no-thinking

A change to existing behaviour in experiments/runs/2026-05-16\_09-44-03\_game-of-life-example-mapping\_v6-hybrid\_sonnet-4-6-no-thinking, experiments/runs/2026-05-16\_09-53-20\_game-of-life-example-mapping\_v6-hybrid\_sonnet-4-6-no-thinking, experiments/runs/2026-05-16\_10-41-18\_game-of-life-example-mapping\_v6-hybrid\_opus-4-6-portkey-no-thinking — 1 commit, 6 files: “data: RQ-12 (Emoji-Effekt cross-model auf sonnet-4-6 und opus-4-6)”.

_experiments/runs/2026-05-16\_09-44-03\_game-of-life-example-mapping\_v6-hybrid\_sonnet-4-6-no-thinking, experiments/runs/2026-05-16\_09-53-20\_game-of-life-example-mapping\_v6-hybrid\_sonnet-4-6-no-thinking, experiments/runs/2026-05-16\_10-41-18\_game-of-life-example-mapping\_v6-hybrid\opus-4-6-portkey-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-05-22\_21-54-21\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-22\_22-25-01\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-22\_22-47-39\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking

A change to existing behaviour in experiments/runs/2026-05-22\_21-54-21\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-22\_22-25-01\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-22\_22-47-39\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking — 1 commit, 9 files: “feat(workflows,runs): v7.1 + v8a/v8b Workflows + initiale Runs”.

_experiments/runs/2026-05-22\_21-54-21\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-22\_22-25-01\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-22\_22-47-39\_claim-office-example-mapping\_v7.1-hybrid-green-refactor-testlist-scope-fix\opus-4-7-portkey-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-05-24\_23-18-18\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-25\_00-20-13\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-25\_00-57-54\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking

A change to existing behaviour in experiments/runs/2026-05-24\_23-18-18\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-25\_00-20-13\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-25\_00-57-54\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking — 1 commit, 9 files: “feat(rq-1.6): v6.2-Cleanup-Validierung gegen v6.1-with-why-Baseline”.

_experiments/runs/2026-05-24\_23-18-18\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-25\_00-20-13\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-25\_00-57-54\_claim-office-example-mapping\_v6.2-with-why-cleaned\opus-4-7-portkey-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-05-25\_09-15-01\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_gemini-3-5-flash, experiments/runs/2026-05-25\_09-28-06\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_kimi-k2-6, experiments/runs/2026-05-25\_10-00-29\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_minimax-m2-7

A change to existing behaviour in experiments/runs/2026-05-25\_09-15-01\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_gemini-3-5-flash, experiments/runs/2026-05-25\_09-28-06\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_kimi-k2-6, experiments/runs/2026-05-25\_10-00-29\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_minimax-m2-7 — 1 commit, 9 files: “feat(harness): Portkey-Routing-Fixes + 4 Modell-Smokes (Pro raus aus v5.1-RQs)”.

_experiments/runs/2026-05-25\_09-15-01\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_gemini-3-5-flash, experiments/runs/2026-05-25\_09-28-06\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\_kimi-k2-6, experiments/runs/2026-05-25\_10-00-29\_claim-office-example-mapping\_v5.1-testlist-scope-fix-oc\minimax-m2-7 · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-07-24\_00-28-34\_claim-office-prose\_v6.2-with-why-cleaned-pi\_opus-4-7-portkey-no-thinking, experiments/runs/2026-07-24\_00-39-23\_claim-office-prose\_v6.2-with-why-cleaned-pi\_opus-4-7-portkey-no-thinking

A change to existing behaviour in experiments/runs/2026-07-24\_00-28-34\_claim-office-prose\_v6.2-with-why-cleaned-pi\_opus-4-7-portkey-no-thinking, experiments/runs/2026-07-24\_00-39-23\_claim-office-prose\_v6.2-with-why-cleaned-pi\_opus-4-7-portkey-no-thinking — 1 commit, 6 files: “data(runs): 2x claim-office-prose v6.2-with-why-cleaned-pi (opus-4-7 requesty)”.

_experiments/runs/2026-07-24\_00-28-34\_claim-office-prose\_v6.2-with-why-cleaned-pi\_opus-4-7-portkey-no-thinking, experiments/runs/2026-07-24\_00-39-23\_claim-office-prose\_v6.2-with-why-cleaned-pi\opus-4-7-portkey-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-07-27\_15-05-24\_claim-office-example-mapping\_v6.6-lab-split-pi\_opus-4-8, experiments/runs/2026-07-27\_15-46-00\_claim-office-example-mapping\_v6.6-lab-split-oc\_opus-4-8-requesty-no-thinking

A change to existing behaviour in experiments/runs/2026-07-27\_15-05-24\_claim-office-example-mapping\_v6.6-lab-split-pi\_opus-4-8, experiments/runs/2026-07-27\_15-46-00\_claim-office-example-mapping\_v6.6-lab-split-oc\_opus-4-8-requesty-no-thinking — 1 commit, 6 files: “data(runs): v6.6-lab-split Smoke-Runs pi/oc/cursor (claim-office, n=1 je)”.

_experiments/runs/2026-07-27\_15-05-24\_claim-office-example-mapping\_v6.6-lab-split-pi\_opus-4-8, experiments/runs/2026-07-27\_15-46-00\_claim-office-example-mapping\_v6.6-lab-split-oc\opus-4-8-requesty-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-08-11\_13-32-45\_game-of-life-example-mapping\_v3-basic-tdd\_opus-5-no-thinking, experiments/runs/2026-08-11\_13-32-45\_game-of-life-example-mapping\_v6.6-lab-split-cc\_opus-5-no-thinking

A change to existing behaviour in experiments/runs/2026-08-11\_13-32-45\_game-of-life-example-mapping\_v3-basic-tdd\_opus-5-no-thinking, experiments/runs/2026-08-11\_13-32-45\_game-of-life-example-mapping\_v6.6-lab-split-cc\_opus-5-no-thinking — 1 commit, 4 files: “feat(kata-dev): RQ 1.3 game-of-life als Referenz-Kata — H2 widerlegt”.

_experiments/runs/2026-08-11\_13-32-45\_game-of-life-example-mapping\_v3-basic-tdd\_opus-5-no-thinking, experiments/runs/2026-08-11\_13-32-45\_game-of-life-example-mapping\_v6.6-lab-split-cc\opus-5-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking, experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking-2, experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking-3

A change to existing behaviour in experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking, experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking-2, experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking-3 — 1 commit, 6 files: “feat(workflows): v6.1.1-lab-split-cc — v6.1 im v6.6-Layout als Export-Traeger”.

_experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking, experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\_opus-5-no-thinking-2, experiments/runs/2026-08-11\_22-40-22\_game-of-life-example-mapping\_v6.1.1-lab-split-cc\opus-5-no-thinking-3 · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-08-16\_06-04-33\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-no-thinking, experiments/runs/2026-08-16\_06-09-51\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-codex-no-thinking

A change to existing behaviour in experiments/runs/2026-08-16\_06-04-33\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-no-thinking, experiments/runs/2026-08-16\_06-09-51\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-codex-no-thinking — 1 commit, 4 files: “feat(rq): RQ-route-effect-pi — Routen-Effekt Requesty vs OpenAI-Subscription”.

_experiments/runs/2026-08-16\_06-04-33\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-no-thinking, experiments/runs/2026-08-16\_06-09-51\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\gpt-5-6-sol-codex-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-08-16\_16-52-25\_game-of-life-prose\_basic-sol-tdd-pi\_gpt-5-6-sol-codex, experiments/runs/2026-08-16\_16-58-02\_game-of-life-prose\_basic-sol-tdd-subagent-pi\_gpt-5-6-sol-codex

A change to existing behaviour in experiments/runs/2026-08-16\_16-52-25\_game-of-life-prose\_basic-sol-tdd-pi\_gpt-5-6-sol-codex, experiments/runs/2026-08-16\_16-58-02\_game-of-life-prose\_basic-sol-tdd-subagent-pi\_gpt-5-6-sol-codex — 1 commit, 4 files: “data(smoke): 2 Marker-Smoke-Runs basic-sol-tdd — gehoeren in keine RQ-Zelle”.

_experiments/runs/2026-08-16\_16-52-25\_game-of-life-prose\_basic-sol-tdd-pi\_gpt-5-6-sol-codex, experiments/runs/2026-08-16\_16-58-02\_game-of-life-prose\_basic-sol-tdd-subagent-pi\gpt-5-6-sol-codex · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-09-03\_23-16-50\_claim-office-example-mapping\_v10-pocock-tdd\_opus-5-no-thinking, experiments/runs/2026-09-03\_23-16-50\_claim-office-example-mapping\_v11-superpowers-tdd\_opus-5-no-thinking

A change to existing behaviour in experiments/runs/2026-09-03\_23-16-50\_claim-office-example-mapping\_v10-pocock-tdd\_opus-5-no-thinking, experiments/runs/2026-09-03\_23-16-50\_claim-office-example-mapping\_v11-superpowers-tdd\_opus-5-no-thinking — 1 commit, 13 files: “runs(rq-4.7): smoke runs for v10-pocock-tdd and v11-superpowers-tdd”.

_experiments/runs/2026-09-03\_23-16-50\_claim-office-example-mapping\_v10-pocock-tdd\_opus-5-no-thinking, experiments/runs/2026-09-03\_23-16-50\_claim-office-example-mapping\_v11-superpowers-tdd\opus-5-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-09-10\_00-35-28\_game-of-life-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-1-no-thinking, experiments/runs/2026-09-10\_00-35-28\_game-of-life-example-mapping\_v6.1-hybrid-testlist-scope-fix\_opus-5-no-thinking

A change to existing behaviour in experiments/runs/2026-09-10\_00-35-28\_game-of-life-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-1-no-thinking, experiments/runs/2026-09-10\_00-35-28\_game-of-life-example-mapping\_v6.1-hybrid-testlist-scope-fix\_opus-5-no-thinking — 1 commit, 4 files: “docs(rq): RQ-2.3 — Fable 5 / Fable 5.1 / Opus 5 auf dem aktuellen Workflow”.

_experiments/runs/2026-09-10\_00-35-28\_game-of-life-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-1-no-thinking, experiments/runs/2026-09-10\_00-35-28\_game-of-life-example-mapping\_v6.1-hybrid-testlist-scope-fix\opus-5-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking, experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking-2, experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking-3

A change to existing behaviour in experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking, experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking-2, experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking-3 — 1 commit, 9 files: “data(rq): RQ-fable-vs-opus5 filled -- Fable 5.1 lands, Fable 5 does not”.

_experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking, experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking-2, experiments/runs/2026-09-10\_19-13-08\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\fable-5-no-thinking-3 · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-09-13\_21-14-47\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-oc\_opus-4-8-requesty, experiments/runs/2026-09-13\_21-22-46\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-cursor\_auto-cursor, experiments/runs/2026-09-13\_21-24-45\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-oc\_opus-4-8-requesty

A change to existing behaviour in experiments/runs/2026-09-13\_21-14-47\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-oc\_opus-4-8-requesty, experiments/runs/2026-09-13\_21-22-46\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-cursor\_auto-cursor, experiments/runs/2026-09-13\_21-24-45\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-oc\_opus-4-8-requesty — 1 commit, 6 files: “feat(export): exact-coding baseline 2026-09-13 from exact-hybrid-v2-testlist-fix on all harnesses”.

_experiments/runs/2026-09-13\_21-14-47\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-oc\_opus-4-8-requesty, experiments/runs/2026-09-13\_21-22-46\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-cursor\_auto-cursor, experiments/runs/2026-09-13\_21-24-45\_game-of-life-example-mapping\_exact-hybrid-v2-testlist-fix-oc\opus-4-8-requesty · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-2, experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-3, experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-5

A change to existing behaviour in experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-2, experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-3, experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-5 — 1 commit, 9 files: “Add remaining Opus 5 EXACT Coding runs”.

_experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-2, experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\_opus-5-requesty-no-thinking-3, experiments/runs/2026-09-14\_17-35-07\_claim-office-example-mapping\_exact-hybrid-v2.4-lab-split-cc\opus-5-requesty-no-thinking-5 · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-09-21\_16-30-48\_game-of-life-python-example-mapping\_exact-ptdd-v1-cc\_opus-5-no-thinking, experiments/runs/2026-09-21\_16-30-49\_game-of-life-python-example-mapping\_exact-ptdd-v1-pi\_gpt-5-6-sol-codex

A change to existing behaviour in experiments/runs/2026-09-21\_16-30-48\_game-of-life-python-example-mapping\_exact-ptdd-v1-cc\_opus-5-no-thinking, experiments/runs/2026-09-21\_16-30-49\_game-of-life-python-example-mapping\_exact-ptdd-v1-pi\_gpt-5-6-sol-codex — 1 commit, 4 files: “Open RQ-exact-coding-python with its two smoke runs”.

_experiments/runs/2026-09-21\_16-30-48\_game-of-life-python-example-mapping\_exact-ptdd-v1-cc\_opus-5-no-thinking, experiments/runs/2026-09-21\_16-30-49\_game-of-life-python-example-mapping\_exact-ptdd-v1-pi\gpt-5-6-sol-codex · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-09-23\_05-25-58\_game-of-life-example-mapping\_exact-ptdd-v1-cc\_opus-5-5-no-thinking, experiments/runs/2026-09-23\_05-25-58\_game-of-life-example-mapping\_exact-subagents-v2-testlist-fix-cc\_opus-5-no-thinking

A change to existing behaviour in experiments/runs/2026-09-23\_05-25-58\_game-of-life-example-mapping\_exact-ptdd-v1-cc\_opus-5-5-no-thinking, experiments/runs/2026-09-23\_05-25-58\_game-of-life-example-mapping\_exact-subagents-v2-testlist-fix-cc\_opus-5-no-thinking — 1 commit, 4 files: “Open RQ-opus55-current-workflow and answer it on Claim Office”.

_experiments/runs/2026-09-23\_05-25-58\_game-of-life-example-mapping\_exact-ptdd-v1-cc\_opus-5-5-no-thinking, experiments/runs/2026-09-23\_05-25-58\_game-of-life-example-mapping\_exact-subagents-v2-testlist-fix-cc\opus-5-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-10-01\_02-28-23\_claim-office-rust-example-mapping\_exact-ptdd-v1-pi\_gpt-6-sol-codex, experiments/runs/2026-10-01\_02-34-42\_claim-office-rust-example-mapping\_exact-ptdd-v1-cc\_opus-5-no-thinking

A change to existing behaviour in experiments/runs/2026-10-01\_02-28-23\_claim-office-rust-example-mapping\_exact-ptdd-v1-pi\_gpt-6-sol-codex, experiments/runs/2026-10-01\_02-34-42\_claim-office-rust-example-mapping\_exact-ptdd-v1-cc\_opus-5-no-thinking — 1 commit, 5 files: “Record the two Rust smoke runs of RQ-exact-coding-rust”.

_experiments/runs/2026-10-01\_02-28-23\_claim-office-rust-example-mapping\_exact-ptdd-v1-pi\_gpt-6-sol-codex, experiments/runs/2026-10-01\_02-34-42\_claim-office-rust-example-mapping\_exact-ptdd-v1-cc\opus-5-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/runs/2026-10-06\_03-14-06\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-cc\_opus-5-no-thinking, experiments/runs/2026-10-06\_03-14-06\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-pi\_gpt-6-1-sol-codex, experiments/runs/2026-10-06\_03-22-01\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-cc\_opus-5-no-thinking

A change to existing behaviour in experiments/runs/2026-10-06\_03-14-06\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-cc\_opus-5-no-thinking, experiments/runs/2026-10-06\_03-14-06\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-pi\_gpt-6-1-sol-codex, experiments/runs/2026-10-06\_03-22-01\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-cc\_opus-5-no-thinking — 1 commit, 9 files: “Add PTDD v1.2 verification split and open RQ-ptdd-verification-split”.

_experiments/runs/2026-10-06\_03-14-06\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-cc\_opus-5-no-thinking, experiments/runs/2026-10-06\_03-14-06\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-pi\_gpt-6-1-sol-codex, experiments/runs/2026-10-06\_03-22-01\_claim-office-example-mapping\_exact-ptdd-v1.2-verification-split-cc\opus-5-no-thinking · medium confidence · unverified

1 commit (0 fixes) modifying experiments/stacks/python-pytest, experiments/stacks/typescript-vitest

A change to existing behaviour in experiments/stacks/python-pytest, experiments/stacks/typescript-vitest — 1 commit, 2 files: “Dispatch the analysis pipeline on the stack and add Python”.

experiments/stacks/python-pytest, experiments/stacks/typescript-vitest · low confidence · unverified

1 commit (0 fixes) modifying misc

A change to existing behaviour in misc — 1 commit, 4 files: “docs(misc): Tampering-Beweisstücke und Projekt-Screenshot ablegen”.

misc · medium confidence · unverified

113 commits (19 fixes) modifying experiments/docker

A change to existing behaviour in experiments/docker — 113 commits (19 fixs), 14 files: “feat(harness): OpenCode-Integration als zweiter Harness neben Claude Code”; “docker(run-batch): truncate run.log to last 500 lines after successful analysis”; “fix(batch): atomic run-dir claim + kimi-k3 auf nebius-Route”; and 110 more.

experiments/docker · medium confidence · unverified

15 commits (0 fixes) modifying experiments/workflows/exact-coding/sol

A change to existing behaviour in experiments/workflows/exact-coding/sol — 15 commits, 214 files: “Evaluate domain boundary and APP variants for SOL TCR”; “feat(workflows): extract TypeScript stack profiles”; “Promote universal versioned PTDD workflow”; and 12 more.

experiments/workflows/exact-coding/sol · medium confidence · unverified

173 commits (30 fixes) modifying experiments

A change to existing behaviour in experiments — 173 commits (30 fixs), 68 files: “Derive RQ state from the data instead of a hand-kept status field”; “Split missed mutants into weak assertions and untested code”; “re-enable self-reported prediction metrics”; and 170 more.

experiments · medium confidence · unverified

182 commits (13 fixes) modifying experiments/runs

A change to existing behaviour in experiments/runs — 182 commits (13 fixs), 64987 files: “Split missed mutants into weak assertions and untested code”; “docs(RQ-19, RQ-3b): Workflow×Modell-Interaktion + v6-hybrid opus-4-6 bereinigt”; “feat(harness): OpenCode-Integration als zweiter Harness neben Claude Code”; and 179 more.

experiments/runs · medium confidence · unverified

2 commits (0 fixes) modifying experiments/runs/2026-05-24\_22-30-28\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-24\_22-40-40\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-24\_22-44-54\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking

A change to existing behaviour in experiments/runs/2026-05-24\_22-30-28\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-24\_22-40-40\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-24\_22-44-54\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking — 2 commits, 9 files: “feat(rq-1.5): Why-Block-Effekt auf v6.1-Basis + neue Workflows v6.1-with-why und v6.2”; “feat(rq-1.6): v6.2-Cleanup-Validierung gegen v6.1-with-why-Baseline”.

_experiments/runs/2026-05-24\_22-30-28\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-24\_22-40-40\_claim-office-example-mapping\_v6.2-with-why-cleaned\_opus-4-7-portkey-no-thinking, experiments/runs/2026-05-24\_22-44-54\_claim-office-example-mapping\_v6.2-with-why-cleaned\opus-4-7-portkey-no-thinking · medium confidence · unverified

2 commits (1 fix) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 2 commits (1 fix), 15 files: “data(RQ-harness-requesty): Cross-Harness-Batch CC/OC/pi opus-4-8 (Requesty), n=5×6”; “fix(pi): Requesty-Ist-Kosten erfassen + opus-4-8-requesty-Route; alle pi-Runs reanalysiert”.

(repo-wide) · medium confidence · unverified

2 commits (1 fix) modifying experiments/docker/pi-config-noreason, experiments/docker/pi-config-reasoning

A change to existing behaviour in experiments/docker/pi-config-noreason, experiments/docker/pi-config-reasoning — 2 commits (1 fix), 12 files: “refactor(workflows)!: lineage-based naming with category folders”; “fix(rq): RQ-route-effect-pi — Reasoning war nicht kontrolliert, Findings korrigiert”.

experiments/docker/pi-config-noreason, experiments/docker/pi-config-reasoning · medium confidence · unverified

21 commits (2 fixes) modifying experiments/katas

A change to existing behaviour in experiments/katas — 21 commits (2 fixs), 165 files: “fix(katas): explicit API contract in all three game-of-life prompts”; “Move research/kata-design to the sister repo kata-builder”; “kata: claim-office (HPSMV/MHPCO) — three prompt styles + design docs”; and 18 more.

experiments/katas · medium confidence · unverified

265 commits (16 fixes) modifying research

A change to existing behaviour in research — 265 commits (16 fixs), 1067 files: “Derive RQ state from the data instead of a hand-kept status field”; “data(runs): 22 cursor-Runs verworfen (Subagent-Praemisse war falsch)”; “Split missed mutants into weak assertions and untested code”; and 262 more.

research · medium confidence · unverified

3 commits (0 fixes) modifying experiments/workflows/external

A change to existing behaviour in experiments/workflows/external — 3 commits, 44 files: “Vendor the Kesseler TDD skill as an external arm”; “refactor(workflows)!: lineage-based naming with category folders”; “Add TCR variant research workflows and SOL results”.

experiments/workflows/external · medium confidence · unverified

4 commits (0 fixes) modifying experiments/workflows/exact-coding/opus

A change to existing behaviour in experiments/workflows/exact-coding/opus — 4 commits, 318 files: “feat(workflows): extract TypeScript stack profiles”; “feat(export): exact-coding baseline 2026-09-13 from exact-hybrid-v2-testlist-fix on all harnesses”; “refactor(workflows)!: lineage-based naming with category folders”; and 1 more.

experiments/workflows/exact-coding/opus · medium confidence · unverified

45 commits (0 fixes) modifying site

A change to existing behaviour in site — 45 commits, 130 files: “Install the EXACT Coding skills for pi in the results site”; “Complete the metric registry and rate only consolidated metrics”; “Write summary.json and export the results site's data”; and 42 more.

site · medium confidence · unverified

99 commits (20 fixes) modifying .claude

A change to existing behaviour in .claude — 99 commits (20 fixs), 48 files: “feat(export): ship red/green/refactor as manual phase controls”; “Derive RQ state from the data instead of a hand-kept status field”; “docs: replace private manuscript path with public Leanpub link”; and 96 more.

.claude · medium confidence · unverified

Fixes

1 commit (1 fix) fixing (repo-wide)

A fix in (repo-wide) — 1 commit (1 fix), 16 files: “Fix three classifier defects the TCR/subagent/hybrid smoke runs exposed”.

(repo-wide) · medium confidence · unverified

1 commit (1 fix) fixing (repo-wide)

A fix in (repo-wide) — 1 commit (1 fix), 193 files: “research: RQ-1 Portkey runs (93/120) + findings + pnpm/Portkey fixes”.

(repo-wide) · medium confidence · unverified

1 commit (1 fix) fixing (repo-wide)

A fix in (repo-wide) — 1 commit (1 fix), 52 files: “research(RQ-harness): bump n=5 + parser fix for OC predictions”.

(repo-wide) · medium confidence · unverified

1 commit (1 fix) fixing (repo-wide)

A fix in (repo-wide) — 1 commit (1 fix), 60 files: “fix(rq-tdd-quality): v8a/v8b refactor symmetry + findings refresh”.

(repo-wide) · medium confidence · unverified

1 commit (1 fix) fixing experiments/runs/2026-07-25\_18-58-58\_game-of-life-example-mapping\_v6.2-with-why-cleaned\_opus-4-8-requesty

A fix in experiments/runs/2026-07-25\_18-58-58\_game-of-life-example-mapping\_v6.2-with-why-cleaned\_opus-4-8-requesty — 1 commit (1 fix), 2 files: “fix(pi): Requesty-Ist-Kosten erfassen + opus-4-8-requesty-Route; alle pi-Runs reanalysiert”.

_experiments/runs/2026-07-25\_18-58-58\_game-of-life-example-mapping\_v6.2-with-why-cleaned\opus-4-8-requesty · medium confidence · unverified

1 commit (1 fix) fixing experiments/runs/2026-07-27\_22-14-50\_claim-office-example-mapping\_v6.6-lab-split-cursor\_opus-cursor, experiments/runs/2026-07-27\_22-45-39\_claim-office-example-mapping\_v6.2.1-phase-continuation-cursor\_opus-cursor

A fix in experiments/runs/2026-07-27\_22-14-50\_claim-office-example-mapping\_v6.6-lab-split-cursor\_opus-cursor, experiments/runs/2026-07-27\_22-45-39\_claim-office-example-mapping\_v6.2.1-phase-continuation-cursor\_opus-cursor — 1 commit (1 fix), 6 files: “data(runs): cursor Subagent-Fix Smoke (n=1 je Workflow, beide gruen)”.

_experiments/runs/2026-07-27\_22-14-50\_claim-office-example-mapping\_v6.6-lab-split-cursor\_opus-cursor, experiments/runs/2026-07-27\_22-45-39\_claim-office-example-mapping\_v6.2.1-phase-continuation-cursor\opus-cursor · medium confidence · unverified

1 commit (1 fix) fixing experiments/runs/2026-08-16\_07-50-05\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-codex-noreason, experiments/runs/2026-08-16\_08-03-20\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-reasoning

A fix in experiments/runs/2026-08-16\_07-50-05\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-codex-noreason, experiments/runs/2026-08-16\_08-03-20\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-reasoning — 1 commit (1 fix), 4 files: “fix(rq): RQ-route-effect-pi — Reasoning war nicht kontrolliert, Findings korrigiert”.

_experiments/runs/2026-08-16\_07-50-05\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\_gpt-5-6-sol-codex-noreason, experiments/runs/2026-08-16\_08-03-20\_game-of-life-example-mapping\_v6.2.1-phase-continuation-pi\gpt-5-6-sol-reasoning · medium confidence · unverified

1 commit (1 fix) fixing experiments/runs/2026-09-05\_14-51-22\_game-of-life-prose\_v3-basic-tdd-pi\_gpt-6-astra-codex-no-thinking

A fix in experiments/runs/2026-09-05\_14-51-22\_game-of-life-prose\_v3-basic-tdd-pi\_gpt-6-astra-codex-no-thinking — 1 commit (1 fix), 2 files: “fix(harness): gpt-6-astra was never declared in models.json”.

_experiments/runs/2026-09-05\_14-51-22\_game-of-life-prose\_v3-basic-tdd-pi\gpt-6-astra-codex-no-thinking · medium confidence · unverified

1 commit (1 fix) fixing experiments/runs/2026-09-10\_10-27-36\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking, experiments/runs/2026-09-10\_10-27-38\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking

A fix in experiments/runs/2026-09-10\_10-27-36\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking, experiments/runs/2026-09-10\_10-27-38\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking — 1 commit (1 fix), 6 files: “Add completed Fable 5 runs (claim-office, v6.1-hybrid-testlist-scope-fix)”.

_experiments/runs/2026-09-10\_10-27-36\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\_fable-5-no-thinking, experiments/runs/2026-09-10\_10-27-38\_claim-office-example-mapping\_v6.1-hybrid-testlist-scope-fix\fable-5-no-thinking · medium confidence · unverified

2 commits (2 fixes) fixing (repo-wide)

A fix in (repo-wide) — 2 commits (2 fixs), 24 files: “fix: cli\_built=false artefact — nudge missing cli.ts, harden prompts”; “research: RQ-1 Portkey runs (93/120) + findings + pnpm/Portkey fixes”.

(repo-wide) · medium confidence · unverified

Test coverage

1 commit adding/updating tests in (repo-wide); 1 commit adding/updating tests in (repo-wide); 1 commit adding/updating tests in (repo-wide); 1 commit adding/updating tests in experiments/runs/2026-05-03\_05-33-40\_game-of-life-prose\_v5-exact-single-context\_haiku-4-5; 1 commit adding/updating tests in experiments/runs/2026-05-04\_07-52-27\_game-of-life-example-mapping\_v5-exact-single-context\_haiku-4-5; 1 commit adding/updating tests in experiments/runs/2026-05-10\_16-05-55\_game-of-life-example-mapping\_v5-exact-single-context\_haiku-4-5-no-thinking; 1 commit adding/updating tests in experiments/runs/2026-05-23\_21-38-24\_claim-office-example-mapping\_v6.1-no-emoji\_opus-4-7-portkey-no-thinking; 1 commit adding/updating tests in experiments/runs/2026-09-04\_11-23-28\_game-of-life-example-mapping\_v6.1.3-refactor-gate-cc\_opus-5-no-thinking; 1 commit adding/updating tests in experiments/runs/2026-09-13\_10-54-15\_claim-office-example-mapping\_exact-hybrid-v2.9-stack-profile-cc\_opus-5-no-thinking; 1 commit adding/updating tests in experiments/runs/2026-09-15\_21-03-16\_game-of-life-prose\_exact-sol-v1.5-tcr-parity-domain-trial-cc\_opus-5-no-thinking; 14 commits adding/updating tests in experiments/tests.

Dependencies

168 commits updating dependencies (2188 manifests)

A dependency / build maintenance change in (dependencies) — 168 commits (9 fixs), 2188 files: “docs(RQ-19, RQ-3b): Workflow×Modell-Interaktion + v6-hybrid opus-4-6 bereinigt”; “feat(harness): OpenCode-Integration als zweiter Harness neben Claude Code”; “data(rq): RQ-astra-native-sol filled -- the native Sol line transfers”; and 165 more.

(dependencies) · medium confidence · unverified

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Baseline

  • First survey — no prior run to compare against. CAI 43.7.

Lenses

  • Code Health 58.5
  • Architecture 85.5
  • Maturity 64.2
  • Readiness 19.0
  • Security 62.5
  • Accessibility 86.0
  • Performance 100.0

Changes since last survey

  • 300 commits — 288 feature/other, 12 fixes

By area

  • experiments/runs — 91 commits
  • research/workflow-dev — 42 commits
  • site/docs — 23 commits
  • research/questions-cross — 21 commits
  • research/questions-claude — 18 commits
  • site/src — 18 commits
  • (root) — 15 commits
  • experiments/docker — 12 commits
  • .claude/skills — 10 commits
  • experiments/workflows — 7 commits
  • research/questions-pi — 6 commits
  • (repo) — 4 commits
  • experiments/compute-cost.py — 3 commits
  • todos_and_ideas/1-IN — 3 commits
  • todos_and_ideas/1-IN.md — 3 commits
  • experiments/measure-suite-transitions.py — 2 commits
  • experiments/stacks — 2 commits
  • research/kata-design — 2 commits
  • research/kata-dev — 2 commits
  • todos_and_ideas/2-ACTIVE — 2 commits

Notable commits

  • fix: Add completed Fable 5 runs (claim-office, v6.1-hybrid-testlist-scope-fix)
  • fix: Fix mutation testing for CLI-driven suites, and fill RQ-current-models-ptdd
  • fix: Fix three classifier defects the TCR/subagent/hybrid smoke runs exposed
  • fix: fix(cost): one list-price source for every pi run, and real tariffs for the codex route
  • fix: fix(export): expose Cursor workflow as exact-coding skill
  • fix: fix(export): ship the two optional skills in every SOL subtree
  • fix: fix(harness): gpt-6-astra was never declared in models.json
  • fix: fix(parser): refactorings_applied auf CC aus Textmarkern statt Phasenquelle
  • fix: fix(pi): kumulative Streaming-Events beim Transkript-Extrakt verwerfen
  • fix: fix(pipeline): env-fault guard, container reanalysis, correct test counting
  • fix: fix(rq): correctness on claim-office follows the spec style, not a test phase
  • fix: fix(tooling): spot-check jq read the wrong block, and tabulate was undeclared
  • change: Add /publish-site, and pull the host prerequisites back into line
  • change: Add Claim Office workshop material: scenarios in prose, design decisions, art prompts
  • change: Add Java EXACT Coding workflow comparison
  • change: Add Java mutation testing via PIT and score RQ-exact-coding-java
  • change: Add PTDD v1.2 verification split and open RQ-ptdd-verification-split
  • change: Add RQ-current-models-ptdd: current models under the maintained PTDD workflow
  • change: Add RQ-exact-coding-rust
  • change: Add RQ-old-vs-new-exact-line-opus55 and fill its two retired-line cells
  • …and 280 more

Architecture

  • 0 containers · 94 bounded contexts · 97 dependency edges (baseline)

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

marcoemrich/agentic_coding_lab was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 17 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 8453d88bc2722ffeea86e5cf9ecc524547057532 — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.84+preprod-d645ca9bbedd.