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

swarm-implement

Skill517 starsChanged 3 days agoMITView on GitHub

Codex adapter for complex implementation work using the canonical opencode-swarm implementation workflow. Use for multi-file features, bug fixes, refactors, risky code changes, or tasks that benefit from exploration, scoped planning, implementation, review, and validation.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read and follow ../../../.opencode/skills/swarm-implement/SKILL.md as the canonical workflow.

    line 10
  2. Very specific:

    Use update_plan for substantial multi-step work.

    line 14
  3. Distinctive:

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

    line 15
  4. Very specific:

    Use apply_patch for manual edits.

    line 16
  5. Distinctive:

    Use focused shell validation after each meaningful change.

    line 17
  6. Very specific:

    Do not invoke OpenCode /swarm commands from Codex unless the user explicitly asks to operate OpenCode Swarm itself.

    line 24

≈ “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

Swarm Implement

Read and follow ../../../.opencode/skills/swarm-implement/SKILL.md as the canonical workflow.

Codex-specific execution notes:

  • Use update_plan for substantial multi-step work.
  • Use the runtime's parallel-execution capability for independent repo reads and searches.
  • Use apply_patch for manual edits.
  • Use focused shell validation after each meaningful change.
  • Bring in narrower skills as needed: $engineering-conventions, $writing-tests, $running-tests, $qa-sweep, or $issue-tracer.
  • Record reviewer and critic verdicts in durable task artifacts. For issue-tracer work, use 08b-implementation-review.md and 09-final-critic.md; otherwise use a task-local review artifact that names verdicts, evidence reviewed, and responses to every blocker.
  • Do not invoke OpenCode /swarm commands from Codex unless the user explicitly asks to operate OpenCode Swarm itself.

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