CLAUDE.md@tests/fixtures/content/banned-references-migration is agent-read markdown (claude) from stbenjam/skillsaw.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Project Standards
summarizer-api wraps two model providers behind one HTTP endpoint. The
deployment pins a model id per environment, so a retired id fails at
request time rather than at build time.
## Model ids
Pin a current model id in `deploy/*.yaml` and nowhere else. When a
provider announces a retirement, run the `model-upgrade` skill — it
carries the replacement table and rewrites the pinned ids.
## Testing
- Run `make test` before every push.
- Record provider responses with `make cassettes` when an id changes;
the recorded fixtures name the model and go stale with it.
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_7vc5p2wg4ypb5wgq
GET https://markdownregistry.com/api/v1/resolve?ref=stbenjam/skillsaw/tests/fixtures/content/banned-references-migration/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/f7266e6951b2f9b4db1158c9117f88cd7ac3ea14ffea80869fadc24390ec8031
Your agent 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.
stbenjam/skillsaw · .agents/skills/skillsaw-issue-solver/SKILL.md · Pick up open GitHub issues from collaborators and create PRs to solve them. Use when triaging and resolving reported…
stbenjam/skillsaw · .agents/skills/skillsaw-issue/SKILL.md · Use when skillsaw reports a likely false positive, misses an edge case, behaves incorrectly, or needs an RFE. Gather a…
stbenjam/skillsaw · .agents/skills/skillsaw-lint/SKILL.md · Use when modifying agentic contextual building blocks like skills (SKILL.md), slash commands, agents, hooks, plugins…
stbenjam/skillsaw · .agents/skills/skillsaw-onboard/SKILL.md · Onboard a repository to skillsaw — run the linter, triage the findings by rule, apply autofixes, manually fix what…
stbenjam/skillsaw · .agents/skills/skillsaw-pr-followup/SKILL.md · Follow up on open PRs in skillsaw — fix failing CI, address reviewer feedback, push updates, and validate backward…
stbenjam/skillsaw · .agents/skills/skillsaw-release-ready/SKILL.md · Audit skillsaw for release readiness — test new rules against real repositories, audit core architectural dimensions…
stbenjam/skillsaw · .agents/skills/skillsaw-release/SKILL.md · Bump the version, generate release notes, and publish a new skillsaw release to PyPI. Use when cutting a new release.
