agentleFS
opendatadiscoveryopendatadiscovery/odd-team/.claude/skills/enumerate/SKILL.md

enumerate

Skill0 starsChanged 2 months agoApache-2.0View on GitHub

Generate or refresh coverage manifest for a scanner — lists ALL items in scope so scans can track progress across sessions.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If exists: this is a re-enumeration (detect new/changed/deleted items)

    line 19
  2. Distinctive:

    If not: this is initial enumeration

    line 20
  3. Very specific:

    Use the appropriate method from state/coverage/README.md enumeration table

    line 23
  4. Very specific:

    Update total_items, scanned_items, coverage_pct

    line 55
  5. Distinctive:

    If re-enumeration: new items added, items changed, items deleted

    line 59
  6. Very specific:

    If $ARGUMENTS is empty, list available scanners and ask which to enumerate

    line 64
  7. Distinctive:

    If target repo doesn't exist locally, report and stop (don't silently skip)

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Enumerate Scanner Scope

Generate or refresh the coverage manifest for scanner at $ARGUMENTS.

Protocol

  1. Read scanner definition at $ARGUMENTS:
    • Extract target repo, scope, and what constitutes an "item"
    • Identify the glob pattern or enumeration method for items in scope
  2. Check for existing manifest at state/coverage/{scanner-id-dashed}.yaml:
    • If exists: this is a re-enumeration (detect new/changed/deleted items)
    • If not: this is initial enumeration
  3. Enumerate all items in scope:
    • Use the appropriate method from state/coverage/README.md enumeration table
    • For code: glob the target repo for matching files/directories
    • For docs: fetch/read SUMMARY.md or file listing
    • For spec: list models/endpoints from spec files
    • Record the current commit hash of the target repo
  4. Write or update manifest at state/coverage/{scanner-id-dashed}.yaml:

    scanner_id: "{scanner-id}"
    scanner_path: "{path to scanner definition}"
    scope_description: "{what's being enumerated}"
    scope_source: "{glob pattern or method used}"
    target_repo: "{relative path to repo}"
    repo_commit_at_enumeration: "{current HEAD commit}"
    last_enumerated: "YYYY-MM-DD"
    total_items: N
    scanned_items: 0
    coverage_pct: 0
    
    items:
      - path: "{relative path within repo}"
        status: not-scanned
      # ... one entry per item
  5. For re-enumeration (manifest already exists):
    • Compare current file list against manifest
    • New files → add with status new
    • Deleted files → mark status deleted
    • For scanned items: check if changed since scan date via git log --since={date} -- {path}
    • Changed items → set status changed-since-scan, record changed_commit
    • Update total_items, scanned_items, coverage_pct
  6. Report:
    • Total items in scope
    • If re-enumeration: new items added, items changed, items deleted
    • Suggested batch size for scanning (aim for 10-15 items per session)

Rules

  • If $ARGUMENTS is empty, list available scanners and ask which to enumerate
  • If target repo doesn't exist locally, report and stop (don't silently skip)
  • Manifest must be deterministically ordered (alphabetical by path) for easy diffing
  • Record exact commit hashes — they're how we detect changes later

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.