agentleFS
Sign inStart free
HippocampusEvolveHippocampusEvolve/universal-agent-seed/.claude/skills/seed-update/SKILL.md

seed-update

Skill0 starsChanged 4 months agoMITView on GitHub

Pull newer Universal Agent Seed machinery (hooks, scripts, skills, configs) into a project that was created from the seed — diff-reviewed, never blind, leaving the project's own knowledge/rules/code untouched. Use when the user runs /seed-update or asks to "update from the seed / sync seed fixes".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Update this copy's machinery from a newer seed at $ARGUMENTS (a seed checkout or an unzipped mise run export archive).

    line 13
  2. Very specific:

    Read docs/UPDATING.md first — it defines the machinery/content boundary.

    line 16
  3. Very specific:

    Compare versions: Read this copy's .seed-version (or .claude-plugin/plugin.json → version) and the source's version.

    line 18
  4. Very specific:

    Verify: run mise run doctor and mise run test-hooks.

    line 31
  5. Very specific:

    If this is a git repo, commit: chore(seed): update machinery to <version>.

    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

Update this copy's machinery from a newer seed at $ARGUMENTS (a seed checkout or an unzipped mise run export archive). If $ARGUMENTS is missing, ask for the path.

Read docs/UPDATING.md first — it defines the machinery/content boundary. Then:

  1. Compare versions. Read this copy's .seed-version (or .claude-plugin/plugin.json → version) and the source's version. If the source is the same or older, say so and stop.
  2. List machinery files (from docs/UPDATING.md): .claude/hooks/**, the seed-provided .claude/skills/{reflect,learn,distill,bootstrap-stack,seed-update}/**, scripts/**, .github/workflows/**, .devcontainer/**, the MCP mirrors, and root config (dprint.json, lefthook.yml, .editorconfig, .gitattributes). For mise.toml, only the [tasks.*] blocks are machinery — preserve the project's [tools] stack choices.
  3. Diff each one (source vs local). Show the user a concise summary of what changed per file. Apply nothing blindly.
  4. Never touch content: .claude/knowledge/*, .claude/rules/core-rules.md, src/, README.md, and the project-specific parts of AGENTS.md. (The <!-- BEGIN learned --> block in AGENTS.md is fine to refresh via mise run mirror-rules.)
  5. Apply the approved changes. Update .seed-version to the source version.
  6. Verify: run mise run doctor and mise run test-hooks; report results.
  7. If this is a git repo, commit: chore(seed): update machinery to <version>.

Be conservative: when a machinery file has local edits that look intentional (not just stale), flag the conflict and ask which version wins rather than overwriting.

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