Skip to content
CAI
Software that uses CAICheck a score

rtk-ai/rtk

61.1

Adequate · 14 November 2026

181k

lines of production code

Rust

primary language

7

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

Features

Add Go ecosystem command support with structured linting and test output

This change introduces a new Go command module (\src/cmds/go\) that enables structured filtering of Go toolchain output. It supports \go test\, \go build\, and \go vet\ by injecting the \-json\ flag to parse NDJSON streaming events, ensuring accurate reporting of test results and build errors. Additionally, it adds support for \golangci-lint\ via \go tool golangci-lint\, including version detection (handling both v1 and v2) and structured JSON output parsing for lint issues.

src/cmds/go · high confidence

Add Ruby ecosystem command filters for Rake, RSpec, and RuboCop

New command modules have been added to the Ruby integration to filter and summarize test and lint output. The Rake module parses Minitest output to show only failures, automatically switching between \rake test\ and \rails test\ based on arguments. The RSpec module injects JSON formatting to provide structured failure summaries, with a text-based fallback. The RuboCop module similarly uses JSON output to group and rank offenses by severity, limiting the displayed results to keep output concise. All three modules leverage \ruby\_exec\ to automatically detect and use \bundle exec\ when a Gemfile is present.

src/cmds/ruby · high confidence

Add SBT (Scala Build Tool) command support

Users can now run SBT tasks directly through the CLI. This change introduces a new \scala\ command module that delegates to \sbt\, supporting standard tasks like \test\, \compile\, and \run\, as well as scoped task notation (e.g., \Test/test\). The implementation includes output filtering to parse and display summaries for ScalaTest and munit, handles integration test scopes, and routes execution through a shared runner for consistent tracking and error handling.

src/cmds/scala · high confidence

Add benchmark session runner script

The \scripts/benchmark-sessions/lib/runner.py\ module has been added to automate the execution of benchmark sessions. This script manages the lifecycle of virtual machines (creating and destroying pools), sets up codebases, configures RTK, runs Claude sessions, and optionally executes terminal-bench precision tests. It handles temporary file cleanup and writes a manifest of the results to the specified output directory.

scripts/benchmark-sessions · high confidence

Added Rust pre-commit hook for code formatting and linting

A new pre-commit hook has been added to automatically format Rust code using cargo fmt and run clippy checks before every commit. This ensures that code is consistently formatted and free of compilation errors (though warnings are allowed) before being committed to the repository.

.claude/hooks/bash · high confidence

Claude Code hook delegates to RTK with environment scrubbing and version guards

The \hooks/claude\ directory now provides a shell-based \PreToolUse\ hook (\rtk-rewrite.sh\) that intercepts commands in Claude Code and rewrites them via the \rtk rewrite\ binary to save tokens. The hook requires \jq\ and \rtk \>= 0.23.0\, caching the version check to reduce spawn overhead. It scrubs the \RTK\_REWRITE\_HOST\ environment variable before delegating to prevent unintended relaxation of approval gates, and handles environment variable prefixes (e.g., \TEST\_SESSION\_ID=2 npx playwright test\) by preserving them in the rewritten command. A comprehensive test suite (\test-rtk-rewrite.sh\) validates these rewrites, including new patterns for npm scripts and Docker Compose commands.

hooks/claude · high confidence

Consolidated PHP tooling with compact output filters

This change introduces a dedicated PHP command module that integrates and filters output for common PHP development tools: PHP syntax checks, Laravel Artisan, PHPUnit, Pest, ParaTest, PHPStan, EasyCodingStandard (ECS), and Pint. Each tool now benefits from standardized output processing—such as stripping ANSI codes, suppressing verbose progress bars, and presenting compact, actionable summaries (e.g., grouping PHPStan errors by file, limiting Pint changes to the top 15 files, or showing only failure diffs for PHPUnit/Pest). The module also handles local tool resolution via Composer's \vendor/bin\ directory, ensuring consistent behavior across different project setups.

src/cmds/php · high confidence

Introduce Pi coding agent extension for bash command rewriting

Added a TypeScript extension (\hooks/pi/rtk.ts\) that integrates with the Pi coding agent to automatically rewrite bash commands using \rtk rewrite\, reducing token usage by mutating commands in-place before execution. The extension subscribes to \tool\_call\ events, delegates to the \rtk\ CLI (requiring version \>= 0.23.0), and includes a version guard that disables the extension if \rtk\ is missing or too old. It is designed to be shared with Oh My Pi (OMP) via a compatibility layer, with install/uninstall logic managed by \rtk init --agent pi\ and ownership tracking handled via a sidecar state file to prevent conflicts between Pi and OMP installations.

hooks/pi · high confidence

Introduce Python ecosystem commands (mypy, pip, pytest, ruff, sqlfluff, uv)

This change adds a new \src/cmds/python\ module that provides filtered, user-friendly output for common Python tooling. It includes \mypy\_cmd\ for grouping type errors by file, \pip\_cmd\ for listing and managing packages (with automatic fallback to \uv\ if \pip\ is missing), \pytest\_cmd\ for summarizing test results and failures, \ruff\_cmd\ for linting and formatting with JSON/text filtering, \sqlfluff\_cmd\ for SQL linting with violation grouping, and \uv\_cmd\ for managing \uv run\ environments while preserving program output. These commands are registered in \mod.rs\ and documented in \README.md\, enabling RTK to intercept and enhance Python tool output for better readability and token efficiency.

src/cmds/python · high confidence

Introduce RTK hook system for command rewriting and suggestions

Added two new shell hooks in .claude/hooks to integrate with Claude Code's PreToolUse:Bash event. The rtk-rewrite.sh hook automatically rewrites supported shell commands to their RTK equivalents using the 'rtk rewrite' binary, handling permission decisions (auto-allow, deny, or ask) and providing optional audit logging. The rtk-suggest.sh hook detects common commands (git, cargo, pnpm, docker, etc.) and suggests RTK alternatives via system messages to highlight potential token savings, without modifying execution.

.claude/hooks · high confidence

Introduce Rust ecosystem command handlers and generic runner

Added new modules in \src/cmds/rust\ to handle Rust-specific tooling. \cargo\_cmd.rs\ implements filtering and summary logic for \cargo build\, \test\, \clippy\, \check\, \install\, and \nextest\, including support for JSON diagnostics and specific output formatting (e.g., preserving \--\ for test flags). \runner.rs\ provides a generic execution layer that runs commands via argument vectors (preserving Clap-parsed boundaries) or an explicit shell script, serving as a fallback for commands without dedicated filters and reusing core error/test runner logic.

src/cmds/rust · high confidence

Introduce configurable AI agent awareness levels

Users can now control how much RTK context is injected into AI coding assistants via a new \\[awareness\]\ configuration table in \\~/.config/rtk/config.toml\. The \level\ setting accepts \default\, \high\, or \full\, allowing operators to choose between a minimal output contract, a version that explains RTK's existence and meta-commands, or a version that instructs agents to prefix every command with \rtk\. This replaces the previous static, single-level awareness text with a tiered approach that reduces token waste for hook-based agents while providing necessary context for rules-only agents.

(repo-wide) · high confidence

Introduce core infrastructure module with shared argument tokenizer and configuration system

This change establishes the \src/core\ module as the central infrastructure layer for the application, providing domain-agnostic building blocks consumed by all other components. It introduces a shared argument tokenizer (\arg\_tokenizer.rs\) that correctly handles complex CLI argument patterns (flags, values, positionals, and \--\ boundaries) across different tool dialects, replacing ad-hoc parsing. The module also includes a robust configuration system (\config.rs\) that manages user settings for tracking, display, filters, telemetry, and hooks, including support for legacy configuration migration. Additionally, it provides a content-addressed recall store (\retriever.rs\) for output recovery, a source code filter engine (\filter.rs\), and various utilities for display formatting, command execution, and telemetry.

src/core · high confidence

Introduce discover module for command history analysis and rewrite logic

The new \src/discover\ module provides two capabilities: it rewrites LLM agent commands (e.g., converting \git status\ to \rtk git status\) via a lexer-aware pipeline that handles shell quoting, redirects, and compound commands, and it analyzes past Claude Code JSONL session files to identify commands that could have been rewritten but were not. This module introduces a shared lexer toolkit for tokenization and shell-splitting, a registry of 60+ rewrite rules with pipeline safety gates, and a reporting system that estimates token savings and adoption rates while distinguishing between measured hook-decision logs and heuristic estimates.

src/discover · high confidence

Introduce native Rust hook engine with multi-agent support and centralized permission decisions

The \src/hooks\ module has been rewritten to replace legacy bash scripts with a native Rust hook system. This change introduces a centralized decision engine (\decision.rs\) that determines whether commands should be rewritten, allowed, or denied based on a strict permission precedence model (Deny \> Ask \> Allow \> Default). The new system supports installation and lifecycle management for a wide range of AI coding agents, including Claude Code, Copilot (VS Code and CLI), Cursor, Gemini, Codex, Trae, Factory Droid, Mistral Vibe, OpenCode, Pi, Oh My Pi, and Hermes. It features SHA-256 integrity verification to prevent tampering, native JSON protocol handling for each agent, and a new \rtk hook audit\ command for tracking rewrite activity. The permission model now enforces that all segments of compound commands must match allow rules to prevent bypasses, and defaults to 'ask' when no rules match, ensuring least-privilege security by default.

src/hooks · high confidence

Introduce plugin system and text utility primitives

This change introduces the \rtk\_plugin\ crate, providing a macro and registration API that allows users to define custom methods and task kinds (such as the demo 'uppercase' method and 'checklist' task) which are then discoverable and executable by the engine. It also adds the \text\ crate, supplying shared text-processing utilities including ANSI code stripping, character-aware truncation, and a 'smart truncate' function that preserves code structure (imports and signatures) when shortening content.

plugin, text · high confidence

Introduce three-tier parser infrastructure with graceful degradation

A new parser module has been added to provide a unified, three-tier system for processing tool outputs: Tier 1 performs complete JSON parsing, Tier 2 falls back to regex-based partial parsing with warnings, and Tier 3 returns truncated raw output if parsing fails entirely. This infrastructure introduces canonical types for test results, lint results, dependency states, and build outputs, along with a token-efficient formatter that supports compact, verbose, and ultra-compressed display modes. Users benefit from more reliable tool integration that degrades gracefully rather than failing silently, with clear degradation markers visible in verbose mode.

src/parser · high confidence

New 'rtk learn' command for detecting and correcting CLI mistakes

A new \rtk learn\ command has been added to analyze Claude Code session history and identify recurring CLI errors, such as unknown flags, wrong paths, or missing arguments. The tool scans session logs to find patterns where a command fails and is subsequently corrected, classifying the error type and calculating a confidence score. Users can view these findings via a console report or JSON output, and optionally auto-generate a \.claude/rules/cli-corrections.md\ file to help prevent these mistakes in future sessions.

src/learn · high confidence

New .NET command module with structured output parsing

Added a new \src/cmds/dotnet\ module that provides structured parsing and filtering for .NET CLI output. The module includes \binlog.rs\ to parse MSBuild binary logs for build and test summaries, \dotnet\_trx.rs\ to parse Visual Studio TRX test result files, and \dotnet\_format\_report.rs\ to parse JSON format reports. The main \dotnet\_cmd.rs\ orchestrates these parsers for \build\, \test\, \restore\, and \format\ subcommands, enhancing output readability and reliability.

src/cmds/dotnet · high confidence

New CI/CD automation and testing scripts

This change introduces a suite of new shell scripts to support continuous integration, local development, and quality assurance. The \scripts/benchmark.sh\ harness compares RTK command performance against standard Unix tools, while \scripts/test-all.sh\ provides a comprehensive smoke test suite for core commands. Additional scripts include \scripts/check-installation.sh\ for verifying the RTK environment, \scripts/check-test-presence.sh\ to enforce unit test coverage on new command modules, and \scripts/test-install.sh\ to validate security fixes against path traversal vulnerabilities. The suite also adds specialized tests for Ruby (\test-ruby.sh\), tracking validation (\test-tracking.sh\), and documentation consistency (\validate-docs.sh\), alongside utility scripts for local installation (\install-local.sh\) and economic impact analysis (\rtk-economics.sh\).

scripts · high confidence

New Git and VCS command modules with output compression

This location introduces a new \src/cmds/git\ module that provides token-optimized wrappers for Git, GitHub CLI (gh), GitLab CLI (glab), and Graphite (gt). The \git\_cmd\ module filters standard Git commands (log, status, diff, show, stash, etc.) to show only essential information, while \gh\_cmd\ and \glab\_cmd\ compress CLI outputs by extracting key fields from JSON responses and filtering markdown noise. The \diff\_cmd\ module provides an ultra-condensed diff view showing only changed lines. These modules work together to reduce output verbosity across version control operations.

src/cmds/git · high confidence

New JVM build tool filters for Maven and Gradle

Added streaming and buffered line filters for JVM build tools to reduce output noise. The Maven filter (\mvn\_cmd.rs\) replaces the previous TOML-based filter with a Rust state machine that collapses passing Surefire test blocks, deduplicates compile errors, handles Maven Daemon (\mvnd\) parallel reactor interleaving, and caps failure summaries. The Gradle filter (\gradlew\_cmd.rs\) provides a streaming filter for \./gradlew\ and \gradle\ commands, filtering task progress and build noise while preserving errors and actionable output.

src/cmds/jvm · high confidence

New JavaScript and TypeScript command modules

Added a new \src/cmds/js\ module providing structured, filtered execution for the JavaScript/TypeScript ecosystem. This includes dedicated commands for Bun (\bun\_cmd\), Deno (\deno\_cmd\), npm/npx (\npm\_cmd\), pnpm (\pnpm\_cmd\), TypeScript (\tsc\_cmd\), Vitest (\vitest\_cmd\), ESLint/Biome (\lint\_cmd\), Prettier (\prettier\_cmd\), Next.js (\next\_cmd\), Playwright (\playwright\_cmd\), and Prisma (\prisma\_cmd\). Each module implements specific output filtering (e.g., stripping ANSI codes, hiding progress bars, grouping diagnostics) and routing through the core runner to ensure consistent, concise user-facing output.

src/cmds/js · high confidence

New analytics dashboards for token savings, economic impact, and session adoption

The \src/analytics\ module now provides read-only dashboards that query the tracking database to report on bash output reduction, economic spending versus savings, and user adoption metrics. This includes the \rtk gain\ command for a token savings dashboard, \rtk cc-economics\ for dual-metric cost analysis (combining \ccusage\ data with RTK tracking), and \rtk session\ for adoption analysis of RTK-routed versus raw commands. These tools parse recorded data to surface savings percentages, spending estimates, and session-level reports without modifying the underlying tracking database.

src/analytics · high confidence

New cloud and infrastructure command modules

Added a new \src/cmds/cloud\ module providing specialized output filters for AWS, container runtimes, and web tools. The AWS module (\aws\_cmd.rs\) covers 25 subcommands (including STS, S3, EC2, ECS, RDS, CloudFormation, CloudWatch Logs, Lambda, IAM, DynamoDB, EKS, SQS, and Secrets Manager), forcing JSON output for structured parsing and using \force\_tee\_hint()\ for truncation recovery. The container module (\container.rs\) handles Docker (ps, images, logs) and Kubernetes/OpenShift (pods, services, logs) with compact summaries and passthrough for unknown subcommands. Additional modules include \curl\_cmd.rs\ (truncates long responses, saves full output for recovery, and passes through binary downloads to prevent UTF-8 corruption), \wget\_cmd.rs\ (strips progress bars, shows result summary), and \psql\_cmd.rs\ (filters PostgreSQL table and expanded display formats into compact output).

src/cmds/cloud · high confidence

New multipass-based integration test suite for RTK

The benchmark scripts now include a comprehensive integration test suite that provisions an Ubuntu 24.04 virtual machine via Multipass. This environment is pre-configured with a wide range of developer tools (Rust, Node.js, Go, Python, .NET, Docker, Kubernetes, etc.) and includes mock implementations for heavy external CLI tools. The suite executes a multi-phase test plan covering cargo quality checks, core RTK commands (git, files, search, data, runners, network, GitHub, cargo, python, go, typescript, linters, docker, k8s, dotnet), and TOML filtering, while also measuring token savings and generating detailed pass/fail reports.

scripts/benchmark · high confidence

New pipeline engine with built-in transformation rules

The engine now provides a configurable pipeline system that processes tool results and agent interactions through a chain of methods. Users can enable built-in pipelines to rewrite shell commands, compress tool outputs (removing ANSI codes, progress bars, and duplicates), delegate large file reads to cheaper models, and enforce terse agent prose. The engine validates these pipelines against strict contracts, ensuring transformations are cache-stable, idempotent where required, and never increase token counts, with a fail-open safety net that preserves original content if any step fails.

engine · high confidence

New system utility commands for code analysis and project inspection

This change introduces a suite of new commands under the system utilities module: \ast-grep\ filters AST-grep plain-mode output by grouping matches and capping results; \ctest\ compacts CTest output while preserving failing-test details and validating summaries; \deps\ summarizes project dependencies from lock files (Cargo.toml, package.json, requirements.txt, pyproject.toml, go.mod); \env\ filters and categorizes environment variables; \find\ filters file search results by grouping and supports both native and RTK syntax; \format\ auto-detects and runs code formatters (Prettier, Ruff, Black, Biome) showing only changed files; \json\ inspects JSON structure with optional schema-only mode and BOM handling; \local\_llm\ provides heuristic-based code summarization without external models; and \log\ captures and summarizes command output. These commands provide token-efficient, filtered views of common development tasks.

src/cmds/system · high confidence

OpenCode plugin now supports version 2.0 and respects agent-scoped permissions

The OpenCode hook plugin has been updated to support both OpenCode 2.0 (using the \execute.before\ hook) and OpenCode 1.18.29+ (using \tool.execute.before\). It now forwards the agent name to the RTK backend for OpenCode 2.x, ensuring that agent-specific permission rules are correctly applied. The plugin also improves reliability by probing for the \rtk hook opencode\ subcommand rather than relying on version numbers, and it strictly resolves the \rtk\ binary from the system PATH to avoid execution issues in OpenCode Desktop or on Windows.

hooks/opencode · high confidence

Unified command execution and output filtering

The \src/cmds\ module now provides a centralized system for executing external CLI tools and filtering their output to reduce token consumption. It organizes command-specific filters by ecosystem (e.g., git, rust, js, python, go, dotnet, cloud, system, ruby, php, scala) and uses a shared runner in \core/runner.rs\ to handle execution, streaming, and tracking. Modules can choose between capture-only, buffered, streaming, or passthrough filter modes depending on the command's output characteristics, ensuring efficient processing while preserving exit codes and tracking token savings.

src/cmds · high confidence

Architecture

Refactored init logic into per-agent submodules

The monolithic \init.rs\ file has been split into dedicated submodules for each supported agent (Antigravity, Claude, Codex, Copilot, Cursor, Droid, Gemini, and Hermes). This change organizes the installation and uninstallation logic for each agent into its own file, improving maintainability and clarity of the codebase without altering the external behavior of the \rtk init\ command.

src/hooks/init · high confidence

Behavioural changes

15 commits (7 fixes) modifying openclaw

A change to existing behaviour in openclaw — 15 commits (7 fixs), 3 files: “fix(hooks): reach deployed hooks with the host scrub, and pin it”; “fix(openclaw): no execSync to avoid async dangerous cmds”; “fix(hooks): pipeline hook rules act on Claude Code only; the shared hook core is develop's again”; and 11 more (refs \#358, \#704).

openclaw · medium confidence · unverified

2 commits (0 fixes) modifying proxy

A change to existing behaviour in proxy — 2 commits, 47 files: “perf(proxy): use mimalloc as the global allocator on musl builds”; “feat(proxy): rtk-proxy daemon, pipelines at the request layer”.

proxy · medium confidence · unverified

Arg tokenizer refactored to use a struct-based Dialect with independent grammar axes

The argument tokenizer's internal grammar model has been restructured: the \Dialect\ type is now a struct composed of independent grammar axes rather than a simple enum. This change enables more granular configuration of tokenization rules while preserving the existing \Posix\ and \Msbuild\ presets. To guarantee backward compatibility, a frozen snapshot of the previous implementation is included and used in exhaustive differential tests that verify every argument vector up to four tokens produces identical tokenization results against the old behavior.

_src/core/arg\tokenizer · high confidence

Major CLI architecture overhaul and removal of legacy modules

The CLI has been completely restructured from a monolithic design into a modular command system. The legacy \filter.rs\, \local\_llm.rs\, \ls.rs\, and \read.rs\ modules have been removed and replaced by a new \cmds\ registry that handles routing for a wide range of tools (Git, npm, Python, Docker, etc.). The \rtk smart\ command no longer uses local LLM models (candle-core/tokenizers) but now uses a fast heuristic analyzer. The \rtk read\ command now supports multiple files and new flags like \--head-lines\ and \--tail\_lines\. The \rtk ls\ command is now a proxy to the native \ls\ command with compact output. The \rtk init\ command now supports multiple AI agents (Claude, Cursor, Trae, Windsurf, Cline, etc.) via the \--agent\ flag.

src · high confidence

Native hook handlers replace bash scripts for supported agents

The hooks directory now provides native hook handlers for supported agents (such as Claude Code, Copilot, Cursor, Codex, and Vibe) instead of relying on external bash scripts. This change introduces agent-specific configuration files, documentation, and test suites within the \hooks/\ directory, while delegating all rewrite logic to the shared RTK Rust binary. Users benefit from improved performance, reduced dependencies (e.g., no longer requiring \jq\ for native handlers), and more robust command interception across a wider range of LLM agents. Also in this area: OpenCode hooks now enforce pipeline blocks and route commands.

hooks/copilot · high confidence

Fixes

18 commits (13 fixes) fixing src/hooks/hook\_cmd

A fix in src/hooks/hook\_cmd — 18 commits (13 fixs), 1 file: “fix(pipeline): swap commands rtk has no filter for”; “fix(pipeline): keep fish scripts out of the swap gate”; “fix(hooks): pipeline hook rules act on Claude Code only; the shared hook core is develop's again”; and 15 more.

_src/hooks/hook\cmd · medium confidence · unverified

7 commits (5 fixes) fixing hooks/hermes/rtk-rewrite

A fix in hooks/hermes/rtk-rewrite — 7 commits (5 fixs), 2 files: “fix(hooks): pipeline hook rules act on Claude Code only; the shared hook core is develop's again”; “feat(hooks): agent plugins honour pipeline block and route”; “fix(hermes): isolate rewrite stdin and make timeout configurable”; and 4 more.

hooks/hermes/rtk-rewrite · medium confidence · unverified

Cursor IDE hook now enforces permission prompts and strict exit codes

The Cursor hook script has been updated to require \rtk \>= 0.23.0\ and \jq\, and now strictly handles permission logic by setting \permission\ to \ask\ when the rewrite tool requests user approval (exit code 3) rather than silently allowing changes. It also ensures the \continue\ flag is present in the JSON output and fails on any exit code other than 0 (allow) or 3 (ask), preventing silent failures or unauthorized rewrites.

hooks/cursor · high confidence

Update Homebrew formula to rtk-ai organization and Apache 2.0 license

The Homebrew formula for rtk has been updated to reflect the project's move to the rtk-ai GitHub organization. Installation instructions and binary download URLs now point to rtk-ai/rtk instead of the previous pszymkowiak/rtk repository. Additionally, the license metadata has been changed from MIT to Apache 2.0, and the homepage URL has been updated to the official project site.

Formula · high confidence

Test coverage

2 commits adding/updating tests in tests/fixtures/git; 8 commits adding/updating tests in hooks/hermes/tests; Added multifail-skeleton test fixture; Added test fixtures for multi-module reactor diagnostics; Added test fixtures for multi-module skeleton; Expanded test coverage for agent hooks, CLI tools, and system integration; Isolated test environment for spawned processes.

Dependencies

Major dependency overhaul and platform support expansion

The project has undergone a significant dependency and configuration overhaul. The license was changed from MIT to Apache-2.0, and the repository URL was updated to rtk-ai/rtk. The Rust edition was upgraded to 2024 with a minimum supported Rust version (MSRV) of 1.91. Local LLM inference capabilities (candle-core, tokenizers, hf-hub) were removed, reducing binary size and complexity. New dependencies were added to support structured output parsing (quick-xml), command tracking via SQLite (rusqlite), TOML configuration (toml, toml\_edit), and improved Windows console code page decoding (windows-sys, codepage, oem\_cp). The build system was also updated to use cargo-deb and cargo-generate-rpm for packaging, replacing the previous cargo-dist setup.

(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 61 → 61 (+0.3)
  • Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 54 → 57 (+3.0)
  • Architecture 94 → 94 (-0.0)
  • Maturity 87 → 87 (-0.3)
  • Readiness 56 → 56 (+0.4)
  • Security 64 → 62 (-1.6)
  • Accessibility 75 (new)
  • Performance 89 → 89 (+0.0)

Resolved (84)

  • Dependency hygiene PARTLY measured — Maven/Gradle declarations read, no dependency graph resolved
  • Duplicated block (10 lines × 2) (src/analytics/gain.rs)
  • Duplicated block (11 lines × 3) (src/cmds/rust/cargo_cmd.rs)
  • Duplicated block (11 lines × 3) (src/core/tracking.rs)
  • Duplicated block (12 lines × 2) (src/cmds/dotnet/dotnet_trx.rs)
  • Duplicated block (12 lines × 2) (src/hooks/permissions.rs)
  • Duplicated block (13–14 lines × 3) (src/analytics/cc_economics.rs)
  • Duplicated block (14 lines × 2) (src/cmds/php/paratest_cmd.rs)
  • Duplicated block (14 lines × 2) (src/core/tracking.rs)
  • Duplicated block (14–15 lines × 2) (src/cmds/dotnet/dotnet_trx.rs)
  • Duplicated block (15 lines × 2) (proxy/src/ccr_forward.rs)
  • Duplicated block (15 lines × 2) (src/core/telemetry_cmd.rs)
  • Duplicated block (17 lines × 2) (src/hooks/init/trae.rs)
  • Duplicated block (26 lines × 2) (src/cmds/system/read.rs)
  • Duplicated block (45–56 lines × 2) (proxy/src/ccr_forward.rs)
  • Duplicated block (5 lines × 2) (src/cmds/git/diff_cmd.rs)
  • Duplicated block (5 lines × 2) (src/cmds/git/glab_cmd.rs)
  • Duplicated block (5 lines × 3) (src/cmds/cloud/container.rs)
  • Duplicated block (5 lines × 3) (src/lib.rs)
  • Duplicated block (6 lines × 2) (proxy/src/memory.rs)
  • …and 64 more

New (200)

  • Duplicated block (10 lines × 2) (src/analytics/gain.rs)
  • Duplicated block (10 lines × 2) (src/core/task_cmd.rs)
  • Duplicated block (10 lines × 2) (src/core/tracking.rs)
  • Duplicated block (11 lines × 3) (src/cmds/rust/cargo_cmd.rs)
  • Duplicated block (12–13 lines × 2) (proxy/src/memory.rs)
  • Duplicated block (12–13 lines × 2) (src/cmds/system/read.rs)
  • Duplicated block (13 lines × 2) (src/cmds/system/read.rs)
  • Duplicated block (13–14 lines × 3) (src/analytics/cc_economics.rs)
  • Duplicated block (14 lines × 2) (src/cmds/php/paratest_cmd.rs)
  • Duplicated block (14 lines × 2) (src/lib.rs)
  • Duplicated block (15 lines × 2) (proxy/src/ccr_forward.rs)
  • Duplicated block (15 lines × 2) (src/core/telemetry_cmd.rs)
  • Duplicated block (16 lines × 2) (src/cmds/system/read.rs)
  • Duplicated block (16–17 lines × 2) (src/cmds/dotnet/dotnet_trx.rs)
  • Duplicated block (18 lines × 2) (src/hooks/init/trae.rs)
  • Duplicated block (21 lines × 3) (src/core/tracking.rs)
  • Duplicated block (3–8 lines × 3) (proxy/src/engine_rules.rs)
  • Duplicated block (5 lines × 2) (src/cmds/git/diff_cmd.rs)
  • Duplicated block (5 lines × 3) (src/cmds/cloud/container.rs)
  • Duplicated block (5 lines × 3) (src/lib.rs)
  • …and 180 more

Changes since last survey

  • 163 commits — 85 feature/other, 78 fixes

By area

  • (repo) — 67 commits
  • src/cmds — 23 commits
  • (root) — 13 commits
  • src/hooks — 13 commits
  • src/discover — 9 commits
  • src/core — 7 commits
  • .github/workflows — 4 commits
  • src/lib.rs — 3 commits
  • docs/contributing — 2 commits
  • docs/guide — 2 commits
  • docs/usage — 2 commits
  • hooks/README.md — 2 commits
  • openclaw/README.md — 2 commits
  • tests/fixtures — 2 commits
  • tests/help_passthrough_fuzz_test.rs — 2 commits
  • .github/assets — 1 commit
  • .github/hooks — 1 commit
  • proxy/Cargo.lock — 1 commit
  • scripts/benchmark.sh — 1 commit
  • tests/fallback_global_flags_test.rs — 1 commit

Notable commits

  • fix: Merge branch 'develop' into fix/swap-unfiltered-commands
  • fix: Merge branch 'develop' into fix/swap-unfiltered-commands
  • fix: Merge develop into codex/fix-rtk-guidance-builtins
  • fix: Merge develop into fix/issue-3980: re-express heredoc guard before redirect_takes_operand
  • fix: Merge pull request #3440 from iliaal/fix/tracking-history-days
  • fix: Merge pull request #3833 from Hubujiu/fix/hermes-modify-directive
  • fix: Merge pull request #3943 from rtk-ai/fix/gain-savings-inflation
  • fix: Merge pull request #3968 from anujsingh-cse/fix/ruff-flag-first-check-routing
  • fix: Merge pull request #4066 from sypsyp97/fix/read-non-utf8-raw-fallback
  • fix: Merge pull request #4152 from KuSh/fix/4117-followup-filtered-log-cap
  • fix: Merge pull request #4175 from Ha1baraA11/codex/fix-rtk-guidance-builtins
  • fix: Merge pull request #4455 from yeahjack/fix/go-test-pipe-text
  • fix: Merge pull request #4461 from spicysharkco/fix/musl-mimalloc
  • fix: Merge pull request #4463 from TechWizard9999/fix/4164-codex-uninstall-exit-code
  • fix: Merge pull request #4628 from Ehsan-hash/fix/dotnet-test-output-artifacts
  • fix: Merge pull request #4647 from nrenvo/fix/read-line-numbers-tab
  • fix: Merge pull request #4658 from webdevsamran/fix/4651-permission-loader-fail-closed
  • fix: Merge pull request #4666 from PavanaSakethaRam/fix/issue-3980-20261019185115-134e064d
  • fix: Merge pull request #4677 from Ehsan-hash/fix/gain-timed-command-classification
  • fix: Merge pull request #4680 from Ehsan-hash/fix/settings-read-fail-closed
  • …and 143 more

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

Survey your own repository

rtk-ai/rtk 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 2a786dca60fa4759f4f8381262a6a3b98256667a — 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.