agentleFS
wedabrowedabro/bro-skills/.github/copilot-instructions.md

bro-skills

Copilot instructions3 starsChanged 45 days agoMITView on GitHub

Project: bro-skills

  • Reads credentials

We split this copilot-instructions.md into the rules it gives an agent

9 rules. About 0 are common, 2 are distinctive, and 7 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.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every task must go through the process: Specify → Plan → Tasks → Implement.

    line 11
  2. Very specific:

    Use Workflows in .agents/workflows/ and Skills in .agents/skills/.

    line 12
  3. Very specific:

    DO NOT hardcoding URLs, Tokens, Keys.

    line 18
  4. Very specific:

    DO NOT run docker compose down -v on Production.

    line 21
  5. Very specific:

    Check logs immediately on error: docker compose logs -f <service>.

    line 23
  6. Distinctive:

    Auto-Commit: MUST perform git commit & push immediately after completing any function or task according to Conventional Commits standards.

    line 24
  7. Very specific:

    Task Tracking: Use task_boundary to synchronize status with @speckit.tasks (tasks.md).

    line 27
  8. Very specific:

    Planning Artifacts: Always create implementation_plan.md when making large changes (atomic > 3 files).

    line 28
  9. Very specific:

    Verification: After completing the task, use walkthrough.md to compare the results with spec.md.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 3,669 Copilot instructions 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
copilot-instructions.md

Copilot Instructions for bro-skills

Project: bro-skills

1. SUPREME ORDER

  • Strictly follow the .agents/memory/constitution.md file.
  • Docker-First: All coding and app running activities must take place in the container. DO NOT run node/python on the host.
  • Ports: Flexibly configure ports via environment variables (.env) to avoid conflicts.

2. bro-skills PROTOCOL

  • Every task must go through the process: Specify → Plan → Tasks → Implement.
  • Use Workflows in .agents/workflows/ and Skills in .agents/skills/.

3. LANGUAGE & CODE

  • Respond in English.
  • 15-Minute Rule: Each task must be atomic, ≤ 15 minutes, affecting ≤ 3 files.
  • PowerShell 5.1+, separate commands with ; (DO NOT use &&).
  • DO NOT hardcoding URLs, Tokens, Keys. Use ENV vars (.env).

4. SAFETY

  • DO NOT run docker compose down -v on Production.
  • Generate automatic scripts (.agents/scripts/) for recurring errors.
  • Check logs immediately on error: docker compose logs -f <service>.
  • Auto-Commit: MUST perform git commit & push immediately after completing any function or task according to Conventional Commits standards.

5. AGENTIC MODE SYNC (Antigravity Only)

  • Task Tracking: Use task_boundary to synchronize status with @speckit.tasks (tasks.md).
  • Planning Artifacts: Always create implementation_plan.md when making large changes (atomic > 3 files).
  • Verification: After completing the task, use walkthrough.md to compare the results with spec.md.

References

  • Constitution: .agents/memory/constitution.md
  • Infrastructure: .agents/knowledge_base/infrastructure.md
  • Workflows: .agents/workflows/
  • Skills: .agents/skills/

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.

Reviews can't be read right now.

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.