Thank you for your interest in contributing to Swarm Command! This project is a Copilot CLI skill — no runtime code, just markdown prompt engineering and documentation.
- Use GitHub Issues to report bugs or suggest improvements
- For security vulnerabilities, see SECURITY.md
- Fork the repository
- Create a feature branch:
git checkout -b my-feature - Make your changes
- Verify the checklist below
- Submit a pull request
Before opening a PR, ensure:
- CI workflow passes (YAML lint + SKILL.md diff)
- All templates have complete DEPTH LOCK blocks for leaf agents
-
catalog.ymlreferences are valid - YAML parses cleanly (
config.yml,catalog.yml) - Depth Guard audit checklist passes (see
protocols/depth-guard.md) - All JSON schemas in
protocols/context-capsule.mdare valid draft-07 - Both SKILL.md copies are identical:
skills/swarm-command/SKILL.md.github/skills/swarm-command/SKILL.md
- Agent counts match across all files (SS-50: ~36-52, SS-100: ~89, SS-250: ~316)
- Agent counts verified via
grep -r "~36-52\|~89\|~316" . - Shadow scoring references use Shadow Score Spec format (no separate shadow validator agents)
- docs/example-output.md reflects current output format (if output format changed)
- Depth Guard is sacred — Workers are ALWAYS leaf nodes (
explore/task). They MUST NOT use thetasktool. - Config is the source of truth — Never hardcode model names, thresholds, or tunables inside prompts.
- All outputs are strict JSON — Every layer boundary uses schema-validated JSON.
- Just a skill — Do not add runtime code, package managers, telemetry, or dashboards.
- Shadow scoring is Nexus-internal — No separate shadow validator agents. Implements Shadow Score Spec L2.
See the README for a full file map.
By contributing, you agree that your contributions will be licensed under the MIT License.