wshobson/agents
55.1
Adequate · 14 November 2026
10.4k
lines of production code
Python
with C#
8
measurements over time
What this system is
Features
Add .NET backend development skill with patterns and templates
A new skill named 'dotnet-backend-patterns' has been added to the .NET contribution plugin, providing guidance and code templates for building production-grade C\#/.NET backends. The skill covers Clean Architecture project structures, dependency injection (including .NET 8 keyed services), async/await best practices, and configuration via IOptions. It includes reference documentation and implementation templates for both Dapper (high-performance SQL) and Entity Framework Core, demonstrating patterns for repository and service layers, caching, validation, and error handling.
plugins/dotnet-contribution/skills · high confidence
Batch plugin evaluation script with per-plugin reporting
A new script, eval\_all.py, has been added to the plugin-eval package to batch-evaluate all local plugins and generate detailed reports. It runs the static evaluation layer on each plugin directory, producing individual JSON result files and a combined markdown summary that highlights mean scores, badge distributions, and plugins with low scores or anti-patterns. The script is designed for CI integration but can also be run locally.
plugins/plugin-eval/scripts · high confidence
Introduce PluginEval CLI for quality scoring and comparison
The \plugin-eval\ package is now available as a Typer-based CLI tool that evaluates Claude Code plugins and skills. It provides \score\ and \certify\ commands to generate quality reports in JSON, Markdown, or HTML, and a \compare\ command for head-to-head skill rankings. The engine supports multiple evaluation depths (Quick, Standard, Deep, Thorough) that combine static analysis, LLM judge assessments, and Monte Carlo simulations, with configurable concurrency and score thresholds. A corpus management system enables Elo-based skill ranking, while a snapshot feature detects changes in static scores to catch regressions in scoring logic.
_plugins/plugin-eval/src/plugin\eval · high confidence
Introduce PluginEval: a quality scoring framework for plugins and skills
The \plugins/plugin-eval\ directory now contains a complete evaluation framework that scores Claude Code plugins and skills across up to three layers: a deterministic static lint, an experimental LLM judge, and an experimental Monte Carlo simulation. Users can run the Typer CLI (\plugin-eval score\, \certify\, \compare\, \init\) to generate composite scores, assign quality badges (Platinum, Gold, Silver, Bronze), and identify anti-patterns. The framework includes a batch evaluation script (\eval\_all.py\) for CI reporting, a corpus management system with Elo ranking, and a set of Claude Code agents (\eval-judge\, \eval-orchestrator\) to assist with the evaluation process. Also in this area: Pin plugin-eval to Python 3.14; Removal of the trace harness and API prompt writer.
plugins/plugin-eval · high confidence
Introduce multi-harness plugin adapters for Codex, Cursor, Copilot, OpenCode, Antigravity, and Pi
The tools/adapters module now provides a unified framework to generate native plugin artifacts for six AI coding assistants from a single set of canonical Markdown sources. This includes new adapter implementations for Google Antigravity CLI (emitting agy plugins with TOML commands and subagents), GitHub Copilot (emitting agent profiles and runnable skills), and Pi (emitting prompt templates and skills), alongside updated adapters for Codex, Cursor, and OpenCode that handle harness-specific constraints like tool-name casing, permission blocks, and body size caps. A central capabilities matrix defines the supported features for each harness, ensuring portable content authoring across the ecosystem.
tools · high confidence
Introduce protect-mcp plugin for policy-gated tool execution and cryptographic audit trails
The new protect-mcp plugin enforces Cedar authorization policies on every Claude Code tool call and produces Ed25519-signed receipts for offline verification. A PreToolUse hook evaluates each call against a user-defined policy file (defaulting to allow if missing) and blocks execution with exit code 2 on deny; a PostToolUse hook appends a signed receipt to ./receipts/receipts.jsonl. The plugin ships with slash commands (/verify-receipt, /audit-chain) and helper agents (policy-enforcer, receipt-verifier) to author policies and verify integrity, along with test fixtures that validate the full evaluate-sign-verify loop. Also in this area: 1 commit (1 fix) fixing plugins/protect-mcp, plugins/review-agent-governance; Protect MCP and Review Agent Governance plugins update to protect-mcp 0.31.1.
plugins/protect-mcp/hooks, plugins/protect-mcp/test · medium confidence · unverified
Introduce review-agent-governance plugin for human-gated AI review actions
Adds the \review-agent-governance\ plugin (v0.1.4) to enforce human approval before AI agents can post PR reviews, comments, merges, or edit CI configuration. The plugin uses \protect-mcp\ (pinned to 0.7.4) and Cedar policies to block review-surface actions by default, requiring a \.review-approved\ flag file or the \/approve-review\ slash command to open a temporary approval window. It includes \PreToolUse\ and \PostToolUse\ hooks to evaluate policies and sign Ed25519 receipts for every allowed tool call, along with a \/list-pending\ command to view blocked actions. The plugin is available for both Claude Code and Codex environments.
plugins/review-agent-governance · high confidence
Introduce three-layer plugin evaluation framework
The plugin evaluation system now uses a three-layer architecture to assess plugin quality. Layer 1 performs deterministic static analysis, checking for anti-patterns (like missing trigger phrases or overly constrained instructions) and scoring structural qualities such as frontmatter quality and orchestration wiring. Layer 2 introduces an LLM-based judge that semantically evaluates skills against rubrics for orchestration fitness, output quality, and scope calibration. Layer 3 implements Monte Carlo simulations to statistically measure reliability, triggering consistency, and token efficiency across multiple runs. A shared SDK helper centralizes message stream processing for both the judge and simulation layers, ensuring consistent handling of model usage and error states.
_plugins/plugin-eval/src/plugin\eval/layers · high confidence
New Cursor-specific agent authoring and project conventions
Added three new rule files to the Cursor configuration that define project conventions, Python tooling standards (uv, ruff, ty), and guidelines for authoring portable agent skills and commands. These rules ensure that plugin content is compatible across multiple AI harnesses, including Cursor, by specifying frontmatter structures, content length limits, and tool-agnostic language requirements.
.cursor · high confidence
New Kubernetes operations skills for GitOps, Helm, and manifest generation
Added three new documentation-based skills to the Kubernetes operations plugin: 'gitops-workflow' provides guidance for implementing GitOps with ArgoCD and Flux CD, including installation, sync policies, and App-of-Apps patterns; 'helm-chart-scaffolding' offers templates and references for creating production-ready Helm charts with security best practices; and 'k8s-manifest-generator' supplies templates and detailed references for generating secure Kubernetes Deployments, Services, and ConfigMaps. These skills provide structured, step-by-step guidance for common Kubernetes deployment and management tasks.
plugins/kubernetes-operations/skills · high confidence
New LLM application development skills for embedding, hybrid search, and LangGraph architecture
Added new skill documentation and reference templates for building modern LLM applications. The \embedding-strategies\ skill provides guidance on selecting and optimizing embedding models (including Voyage AI and OpenAI) and chunking strategies for RAG. The \hybrid-search-implementation\ skill introduces patterns for combining vector and keyword search using methods like Reciprocal Rank Fusion (RRF) and linear combination, with specific examples for PostgreSQL. The \langchain-architecture\ skill details the use of LangChain 1.x and LangGraph for building agents, managing state, and implementing memory systems. Additionally, the \llm-evaluation\ skill offers strategies for automated metrics and LLM-as-judge evaluation, while \prompt-engineering-patterns\ includes templates for few-shot learning, chain-of-thought, and structured outputs.
plugins/llm-application-dev/skills · high confidence
New PPTX Deck Creation plugin for generating editable PowerPoint decks
The \plugins/pptx-deck-creation\ plugin is now available, enabling the creation of production-ready, editable PowerPoint decks through a spec-first workflow. It provides skills for preparing business narratives, authoring coordinate-explicit slide specifications, analyzing reference decks in read-only mode, and applying quality gates for geometry and accessibility. The plugin uses a task-local \python-pptx\ builder to generate native editable objects (text, shapes, tables) based on inch-based JSON contracts, ensuring source decks are never mutated and supporting safe OOXML package inspection.
plugins/pptx-deck-creation · high confidence
New backend development skills for API design, architecture, and event-driven patterns
The backend-development plugin now includes five new specialized skills: \api-design-principles\ provides guidance and a production-ready FastAPI template for building REST and GraphQL APIs; \architecture-patterns\ covers Clean, Hexagonal, and Domain-Driven Design with implementation examples; \cqrs-implementation\ details Command Query Responsibility Segregation patterns; \event-store-design\ guides the setup of event stores for event-sourced systems; and \saga-orchestration\ (referenced in architecture patterns) supports distributed transaction management. These skills equip developers with structured approaches to designing scalable, maintainable backend systems.
plugins/backend-development/skills · high confidence
Fixes
4 commits (3 fixes) fixing plugins/dgx-spark-ops
A fix in plugins/dgx-spark-ops — 4 commits (3 fixs), 13 files: “fix(codex): publish only native packages with source skills (\#752)”; “fix: bump changed plugins and require version bumps in CI (\#799)”; “fix: issue triage — grounded-vault skill, $ARGUMENTS framing, agent copy reconciliation (\#694)”; and 1 more (refs \#752, \#799, \#694, \#624).
plugins/dgx-spark-ops · medium confidence · unverified
Test coverage
Added comprehensive test suite for the plugin-eval evaluation engine
This change introduces a new test suite in \plugins/plugin-eval/tests\ that validates the plugin evaluation capabilities. The tests cover the CLI interface (score, certify, compare commands), the core evaluation engine (static, judge, and Monte Carlo layers), and specific features like Elo ranking, corpus management, and portability analysis. It also includes end-to-end tests against real plugins and ensures that warnings for unmeasured judges and depth downgrades are correctly surfaced to users.
plugins/plugin-eval/tests · high confidence
Dependencies
Migrate plugin-eval to pyproject.toml and update yt-design-extractor dependencies
The plugin-eval tool has been scaffolded with a pyproject.toml manifest, replacing previous dependency management methods and specifying Python 3.12+ requirements along with core dependencies like pydantic, typer, rich, and pyyaml, as well as dev tools including pytest, ruff, and ty. The yt-design-extractor tool has also been migrated to pyproject.toml, updating its dependency list to include yt-dlp (version 2026.7.4 or higher), youtube-transcript-api, Pillow, pytesseract, and colorthief, while maintaining an optional easyocr extra. Additionally, a new requirements.txt file was added for the pptx-deck-creation plugin's reference deck analysis skill, pinning defusedxml to versions \>=0.7 and \<1.
(dependencies) · high confidence
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
Score
- CAI 57 → 55 (-1.7)
- Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.
Lenses
- Code Health 71 → 58 (-12.4)
- Architecture 88 → 86 (-1.7)
- Maturity 80 → 93 (+12.9)
- Readiness 35 → 36 (+1.7)
- Security 75 → 75 (-0.4)
- Performance 100 → 100 (+0.0)
Resolved (42)
- Classify ADR enforcement: Architecture Decision Records (plugins/documentation-generation/skills/architecture-decision-records/SKILL.md)
- Critical CVE: [GHSA redacted] (tools/yt-design-extractor/uv.lock)
- Critical vulnerability: [GHSA redacted] (plugins/plugin-eval/uv.lock)
- Critical vulnerability: [GHSA redacted] (tools/yt-design-extractor/uv.lock)
- Duplicated block (8 lines × 2) (tools/validate_generated.py)
- FileTooLong: tools/doc_gardener.py (tools/doc_gardener.py)
- FileTooLong: tools/validate_generated.py (tools/validate_generated.py)
- High CVE: [GHSA redacted] (tools/yt-design-extractor/uv.lock)
- Low vulnerability: [GHSA redacted] (tools/yt-design-extractor/uv.lock)
- Medium CVE: [GHSA redacted] (plugins/plugin-eval/uv.lock)
- Off-boarding risk: anonymized user #1
- base.context_paragraph (cognitive 18) (tools/adapters/base.py)
- base.parse_frontmatter (cognitive 61) (tools/adapters/base.py)
- base.parse_frontmatter (cyclomatic 36) (tools/adapters/base.py)
- cursor._validate_mdc_frontmatter (cognitive 16) (tools/adapters/cursor.py)
- doc_gardener.check_agent_divergence (cognitive 17) (tools/doc_gardener.py)
- doc_gardener.check_arguments_framing (cognitive 44) (tools/doc_gardener.py)
- doc_gardener.check_arguments_framing (cyclomatic 20) (tools/doc_gardener.py)
- doc_gardener.check_dead_links (cognitive 18) (tools/doc_gardener.py)
- doc_gardener.check_generated_frontmatter_yaml (cognitive 27) (tools/doc_gardener.py)
- …and 22 more
New (15)
- Duplicated block (9 lines × 2) (plugins/plugin-eval/src/plugin_eval/parser.py)
- Edited copies of one member (3 members, 8+ corresponding lines) (tools/adapters/antigravity.py)
- Edited copies of one member (4 members, 17+ corresponding lines) (tools/adapters/antigravity.py)
- Edited copy of a member (10 corresponding lines) (tools/install_opencode.py)
- Edited copy of a member (13 corresponding lines) (plugins/pptx-deck-creation/skills/pptx-reference-deck-analysis/scripts/inspect.py)
- Edited copy of a member (14 corresponding lines) (tools/adapters/antigravity.py)
- Edited copy of a member (15 corresponding lines) (tools/install_copilot.py)
- Edited copy of a member (17 corresponding lines) (tools/install_opencode.py)
- Edited copy of a member (22 corresponding lines) (tools/adapters/copilot.py)
- Edited copy of a member (6 corresponding lines) (tools/install_antigravity.py)
- Edited copy of a member (7 corresponding lines) (plugins/pptx-deck-creation/skills/pptx-reference-deck-analysis/scripts/inspect.py)
- Edited copy of a member (8 corresponding lines) (tools/adapters/base.py)
- Off-boarding risk: anonymized user #1
- Repeated repair: plugins/plugin-eval/src/plugin_eval/parser.py (plugins/plugin-eval/src/plugin_eval/parser.py)
- parser._strip_fenced_blocks (cognitive 20) (plugins/plugin-eval/src/plugin_eval/parser.py)
Changes since last survey
- 18 commits — 10 feature/other, 8 fixes
By area
- (root) — 4 commits
- plugins/plugin-eval — 4 commits
- tools/yt-design-extractor — 4 commits
- .cursor-plugin/plugins — 1 commit
- plugins/llm-application-dev — 1 commit
- plugins/protect-mcp — 1 commit
- plugins/python-development — 1 commit
- plugins/security-scanning — 1 commit
- plugins/shell-scripting — 1 commit
Notable commits
- fix: fix(deps): resolve open Dependabot security alerts (#798)
- fix: fix(plugin-eval): exclude code spans and fenced blocks from cross-reference extraction (#810)
- fix: fix(security-scanning): remove references to unshipped SAST helper files (#792)
- fix: fix(shell-scripting): clear SkillSpector findings in bash-defensive-patterns (#808)
- fix: fix: bump changed plugins and require version bumps in CI (#799)
- fix: fix: correct 22 broken code examples reported in #790 (#797)
- fix: fix: include dev dependencies in test targets (#785)
- fix: fix: upgrade governance initialization and evaluation to 0.32.4 (#805)
- change: Add a compact Milvus Lite recipe to the RAG reference (#804)
- change: chore(marketplace): remove the external hol-guard entry (#811)
- change: deps(plugin-eval): bump mcp in /plugins/plugin-eval (#783)
- change: deps(plugin-eval): bump the python-minor-and-patch group (#781)
- change: deps(plugin-eval): bump the python-minor-and-patch group (#803)
- change: deps(yt-design-extractor): bump setuptools in /tools/yt-design-extractor (#789)
- change: deps(yt-design-extractor): bump the python-minor-and-patch group (#802)
- change: deps(yt-design-extractor): bump yt-dlp (#794)
- change: docs: lead the README with the adapter and validation design (#809)
- change: feat(marketplace): add external deja-vu memory entry (#812)
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
wshobson/agents 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 14 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 9c61ab243def98f72da12abd41cfcf5bcd91af9d — 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-2026.11.65+preprod-36d4cd83012f.