agentleFS
Sign inStart free
ZaxbyHubZaxbyHub/opencode-swarm/.agents/skills/engineering-conventions/SKILL.md

engineering-conventions

Skill517 starsChanged 3 days agoMITView on GitHub

Codex adapter for opencode-swarm engineering invariants. Use before modifying plugin initialization, subprocesses, runtime portability, .swarm containment, plan durability, test_runner behavior, test-writing patterns, session/global state, guardrails/retry semantics, chat/system hooks, tool registration, release/cache hygiene, or related architecture.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this adapter before any change that can touch a repository invariant.

    line 10
  2. Very specific:

    If editing agent prompt strings or escaped template text, pay attention to the "Agent prompt strings — escaping pitfalls" section, which is …

    line 18
  3. Very specific:

    Use apply_patch for manual edits.

    line 22
  4. Very specific:

    Use the available shell execution tool for rg, git, build, smoke, and test commands.

    line 23
  5. Distinctive:

    Use the runtime's parallel-execution capability for independent file reads and searches.

    line 24
  6. Distinctive:

    Keep changes scoped and produce concrete invariant evidence for every touched invariant.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Engineering Conventions

Use this adapter before any change that can touch a repository invariant.

Read, in order:

  1. AGENTS.md
  2. docs/engineering-invariants.md
  3. .opencode/skills/engineering-conventions/SKILL.md

If editing agent prompt strings or escaped template text, pay attention to the "Agent prompt strings — escaping pitfalls" section, which is now carried in both the .opencode summary (item 3 above) and .claude/skills/engineering-conventions/SKILL.md.

Codex-specific execution notes:

  • Use apply_patch for manual edits.
  • Use the available shell execution tool for rg, git, build, smoke, and test commands.
  • Use the runtime's parallel-execution capability for independent file reads and searches.
  • Keep changes scoped and produce concrete invariant evidence for every touched invariant.

The source of truth is always AGENTS.md. If an imported skill conflicts with it, AGENTS.md wins.

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