Queue a code review mission (ex: /review https://github.com/owner/repo/pull/42).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## Large diffs & partial-coverage reporting
Review diffs are packed to fit a token budget by the diff compressor
(`optimizations.review_compressor.token_budget`, default 80,000 tokens — the
single knob controlling review diff size). The fetch-time character cap is
*derived* from that budget (budget × 3.5 chars/token × 4 headroom), so on
large-context models the compressor — not a blind character cut — decides
coverage. When the compressor is disabled, a token-safe backstop (budget × 3.5,
no headroom) truncates the diff so the size guard holds in every config.
Whenever any file is omitted (fetch-time backstop, compressor packing, or
trivial-file triage), the posted review opens with a `⚠️ Partial review` block
listing every omitted file, so partial coverage is never silent.
The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_agqjo2lnyk56qhvg
GET https://markdownregistry.com/api/v1/resolve?ref=anantys-oss/koan/review
GET https://markdownregistry.com/api/v1/blob/e1e5e1ff871907e340ea087211cb075c6f99f04e537bbd213bb8363ab630ebc6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
anantys-oss/koan · .claude/skills/brain/SKILL.md · Consult, capture, and acquire knowledge in koan's OKF-conformant docs/ and specs/ bundles. Use for /brain ask…
anantys-oss/koan · .claude/skills/speckit-analyze/SKILL.md · Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after…
anantys-oss/koan · .claude/skills/speckit-clarify/SKILL.md · Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and…
anantys-oss/koan · .claude/skills/speckit-constitution/SKILL.md · Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent…
anantys-oss/koan · .claude/skills/speckit-converge/SKILL.md · Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new…
anantys-oss/koan · .claude/skills/speckit-implement/SKILL.md · Execute the implementation plan by processing and executing all tasks defined in tasks.md
anantys-oss/koan · .claude/skills/speckit-plan/SKILL.md · Execute the implementation planning workflow using the plan template to generate design artifacts.
anantys-oss/koan · .claude/skills/speckit-tasks/SKILL.md · Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
anantys-oss/koan · .claude/skills/speckit-taskstoissues/SKILL.md · Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design…
qwenlm/qwen-code · packages/core/src/skills/bundled/review/SKILL.md · Review changed code for correctness, security, code quality, and performance. Use when the user asks to review code…
suboss87/fdeops · skills/review/SKILL.md · Review a proposed customer code change against its intended outcome and operational risks. Use for a diff or PR review…
snowflake-labs/cocoplus · .cortex/skills/cocobrew/review/SKILL.md · Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec…
