agentleFS
Sign inStart free
arbelharbelh/perdure/skills/coverage/SKILL.md

coverage

Skill0 starsChanged 28 days agoMITView on GitHub

Check the records against the population of sessions — how much of

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use scan, lint and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • rajnavakotiSkill

    scan

    Run the AI dashboard scanner and generate the HTML report.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    lint

    Run all linting and spell checking for TypeScript and Rust code. Run this before committing to catch style issues, clippy warnings, and misspellings.

    Also in 4 projects that use this

  • julienamorganSkill

    profile

    Researches the user's market, competitors, and competitive positioning to build a complete ICP profile. Shows findings for user approval before proceeding. Triggers: /profile, "research my market", "who are my competitors". Reads: ./gtm/company.md, ./gtm/icp.md. Writes: updates ./gtm/icp.md with competitive positioning. Standalone: yes (asks for domain if company.md missing).

    Also in 3 projects that use this

  • asterkinSkill

    adr

    Create Architecture Decision Records (ADRs) following project standards. Guides template usage, process, and best practices for documenting architecturally significant decisions.

    Also in 4 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 3 projects that use this

  • MicrosoftSkill

    worktree

    Create, reuse or clean up a dedicated git worktree for working on a pull request or a private branch. Use from any PR-scoped workflow that needs an isolated checkout to keep current code and build output untouched.

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

Coverage — records checked against what actually ran

Reads the session index that raw builds.

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/coverage.py" --root .

Without ${CLAUDE_PLUGIN_ROOT}, the script sits in the plugin checkout's root scripts/ directory (Codex keeps the whole checkout), or in scripts/ beside this SKILL.md (skills CLI).

Requires the session index (/perdure:raw first). Three buckets, in descending strength of evidence:

  • CITED — a record's frontmatter names the session id. Checkable. Deliberately not "a UUID appears somewhere in the record": that counted a quoted log line, and a sentence declining to record a session, as evidence.
  • WEAK — a body mention, or a record whose window intersects the session's. Correlation, not evidence — say so when you report it.
  • UNEXPLAINED — neither.
  • UNEVALUABLE — no usable timestamps, so no check was possible. Report this separately: "I could not check" is not "I found nothing".

How to report it

  1. Never call an unexplained session a violation. The convention's rule: "Skip the record only when the whole task is one line in one file (a typo, a one-line fix), or a question or brainstorm that decides nothing." Many sessions in a healthy project are exactly that and legitimately have no record. This tool cannot know which; that judgement is the reader's.
  2. Say which numbers are checkable. CITED is evidence. OVERLAPPING is a hint, and must be described as one.
  3. Read records-without-sessions carefully. The population is the sessions started in the project's folder, a subfolder of it, or a worktree under it. Records describe a repository, and one session routinely edits a repo other than the one it started in. Work done from a session started elsewhere is invisible here. Say so rather than implying records are missing.
  4. To make coverage checkable, add the session id to a record's frontmatter: sessions: <id>. Until records cite sessions, only the heuristic is available and the honest answer is "not established".

--strict --min-prompts N exits 1 on unexplained sessions with at least N prompts, for CI. The bar is explicit on purpose: there is no defensible universal threshold for "this should have been recorded".

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free