agentleFS
Sign inStart free
pkhamrepkhamre/skills/AGENTS.md

skills

AGENTS.md1 starsChanged 3 months agoMITView on GitHub

A public collection of authored opencode skills for GitHub (pkhamre/skills). There is no application code, no build, and no test or lint tooling. There is nothing to compile or run in CI; the deliverable is the markdown under skills/ plus the root README.md. skills/continuity/session-handoff/ is the tracked canonical source. .agents/skills/session-handoff/ is the installed copy opencode actually loads. They are out of sync right now: the installed copy predates the decision-log refactor. Editing one does not touch the other. If you…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository5 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    No rasterizer is available in this environment (no cairo/rsvg/inkscape/browser, no network).

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

AGENTS.md

What this repo is

A public collection of authored opencode skills for GitHub (pkhamre/skills). There is no application code, no build, and no test or lint tooling. There is nothing to compile or run in CI; the deliverable is the markdown under skills/ plus the root README.md.

Where things live

  • skills/<category>/<name>/ — canonical, tracked authored skills. Each has SKILL.md (frontmatter name + description; the description drives triggering) and optionally references/, scripts/, or assets/.
  • .agents/skills/ and skills-lock.json — installed upstream skills and the opencode install manifest. Both are gitignored. Do not commit them.
  • assets/readme/ — hand-authored SVG images embedded in the README.
  • docs/ — session docs (HANDOFF, SESSION_LOG, DECISIONS, RUNBOOK), maintained via the session-handoff skill.

Gotcha: two copies of session-handoff, not synced

skills/continuity/session-handoff/ is the tracked canonical source. .agents/skills/session-handoff/ is the installed copy opencode actually loads. They are out of sync right now: the installed copy predates the decision-log refactor. Editing one does not touch the other. If you change session-handoff, update both and keep their content aligned.

Skill relationships

  • decision-log records decisions in docs/DECISIONS.md. session-handoff delegates decision capture to it and must not maintain DECISIONS itself. Preserve this split.
  • Both live under skills/continuity/. New authored skills go under a category subdirectory, not directly under skills/.

Writing rules for prose

README and skill bodies are public-facing. Keep bodies under a few hundred lines and push detail into references/. Run new or edited prose through the anti-ai-slop-writing skill: no em dashes over budget, no banned words, no rule-of-three, varied sentence length. The README currently has zero em dashes and zero banned words; don't regress it.

Verifying SVG assets

No rasterizer is available in this environment (no cairo/rsvg/inkscape/browser, no network). Verify hand-edited SVGs by XML well-formedness and the bundled audit script:

python3 .agents/skills/beautify-github-readme/scripts/audit_readme.py README.md

Session workflow

On an explicit session start/resume/end command, follow the session-handoff skill: read README.md, docs/HANDOFF.md, the latest docs/SESSION_LOG.md entry, docs/DECISIONS.md, docs/RUNBOOK.md in that order, and update HANDOFF + SESSION_LOG when wrapping up.

Git state

Remote origin is git@github.com:pkhamre/skills.git; main tracks origin/main and is currently ahead of it by unpushed commits. Prefer the README's npx skills add pkhamre/skills commands for install references.

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