agentleFS
jctotsjctots/thinkpad-fedora-agent/.claude/skills/vendor-update/SKILL.md

vendor-update

Skill0 starsChanged 3 months agoMITView on GitHub

Check every vendored component in VENDOR.md against its upstream, walk the Local Changes table, and write findings to .claude/proposals/ — never applied directly. Human-invoked, occasional cadence — no natural trigger event to run this proactively.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. apache/skywalking-banyandb★ 355same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Follow VENDOR.md's own "Refreshing a vendored component" section — that's the authoritative procedure, this skill just executes it.

    line 6
  2. Distinctive:

    If nothing has changed upstream for a component since the pinned commit, say so plainly rather than writing an empty proposal — this …

    line 45

≈ “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

Follow VENDOR.md's own "Refreshing a vendored component" section — that's the authoritative procedure, this skill just executes it. Re-read that section first; it's short and this summarizes it:

  1. For each entry in VENDOR.md with a real upstream URL (skip entries whose "Vendored to" says "nothing — reimplemented", there's no commit to diff): fetch upstream at its current default branch and diff against the pinned commit for the specific vendored path(s), not the whole upstream repo.

    gh api repos/<owner>/<repo>/compare/<pinned-sha>...HEAD --jq '.files[] | select(.filename | startswith("<vendored-path>")) | .filename'

    or, without gh, a shallow clone and git log <pinned-sha>..HEAD -- <path>.

  2. Read the diff, don't merge it. The agent's job here is analysis, not application — .claude/hooks/ and any file this repo vendors code into are agent-denied on the write path by design.
  3. Take harness/mechanism changes only, never the pattern set. Per VENDOR.md: _ruleset.py's rules are this repo's own and are never merged from upstream, since upstream's tiering forbids ordinary work on this machine. Report what changed upstream, but don't propose pulling in rule changes.
  4. Walk the Local Changes table for that component, row by row, against the new upstream source. A local change upstream has since adopted independently gets marked for deletion from the table (it's no longer this repo's own contribution) — don't leave it claiming credit for something upstream now does natively.
  5. Write findings to .claude/proposals/P{nnn}-{slug}.md — the diff, what it means for the Local Changes table, and an explicit recommendation (take the harness change / don't / not applicable). Never apply the code directly: VENDOR.md is explicit that a human applies vendored code and runs make probe afterward, and a wrong harness refresh can break the ASK path silently (exit 0 with a malformed body reads as "no rule matched").
  6. If nothing has changed upstream for a component since the pinned commit, say so plainly rather than writing an empty proposal — this skill's value is in catching drift, and "checked, nothing to do" is a valid, useful outcome to report back.

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.