agentleFS
benjamin-smallbenjamin-small/agentic-harness-development/skills/poietic-harness-update/SKILL.md

poietic-harness-update

Skill0 starsChanged 42 days agoMITView on GitHub

Check Poietic Harness toolkit version alignment or update its installed skills and runtime to an exact GitHub release. Use for poietic-harness:update, startup version mismatches, or requests to upgrade this guidance repository. Preserves project pins and scoped local expertise.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check before changing anything.

    line 12
  2. Distinctive:

    Run the read-only check. Distinguish a pinned version mismatch from availability of a newer release and from an unavailable check.

    line 23
  3. Distinctive:

    Keep the prior version available for rollback.

    line 28
  4. Very specific:

    Search this component with rg before loading more context.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Poietic Harness update

Check before changing anything. A session-start check reports version alignment; it does not authorize an upgrade or a change to a project/deployment pin. An explicit update request authorizes work within its stated scope.

Routine version polling should invoke the deterministic maintenance executable directly, without an agent turn. Use checking guidance for the available command, cache/exit semantics, and host network permissions.

  1. Locate the active installation and project root from the invoking harness's configured paths. Read the knowledge index, then only the topic needed. Do not assume the current directory is the toolkit.
  2. Run the read-only check. Distinguish a pinned version mismatch from availability of a newer release and from an unavailable check.
  3. For an update request, follow the scoped update procedure. Inspect the target changelog, verify release artifacts, stage separately, preserve local edits and knowledge/memory, then switch the intended consumer. Keep the prior version available for rollback.
  4. Recheck the actual installed consumer and report version, scope, destinations, integrity verification, and any required session restart or unresolved conflict.

Search this component with rg before loading more context. Maintain this skill's own writable knowledge/local/ and memory/local/ under its user, project, or deployment working copy. Never write learned state into an immutable release or plugin cache. Consult memory for reviewed lessons; record only observed, scoped lessons with evidence and dates.

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.