agentleFS
BaelfyreBaelfyre/Kaos/.github/copilot-instructions.md

Kaos

Copilot instructions27 starsChanged 5 months agoMITView on GitHub

When assisting in the Kontrolled Kaos repository or working with Kontrolled Kaos-integrated workspaces, adhere strictly to the following architectural, routing, and governance principles:

The file

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

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    When assisting in the Kontrolled Kaos repository or working with Kontrolled Kaos-integrated workspaces, adhere strictly to the following …

    line 3
  2. Distinctive:

    Run project validations after changes:

    line 48
  3. Distinctive:

    Do not remove files, rename files, change public APIs, change database schemas, or run destructive commands without explicit user approval.

    line 52
  4. Distinctive:

    Keep secrets, tokens, credentials, and private data out of code, logs, and prompt artifacts.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 3,779 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

GitHub Copilot Instructions for Kontrolled Kaos

When assisting in the Kontrolled Kaos repository or working with Kontrolled Kaos-integrated workspaces, adhere strictly to the following architectural, routing, and governance principles:

1. Governance and Routing Architecture

  1. Governance Layer: The Steward (business alignment, scope, SDLC) and The Governor (legal, compliance, privacy, IP, licensing) sit above the Conductor. The Conductor cannot override governance decisions.
  2. Routing Layer: Conductor is the exclusive internal specialist router and workflow orchestrator. Do not invent custom subagent chains or bypass Conductor for complex tasks. For clear single-owner work, Conductor may select a direct single-specialist fast route. That route is still a Conductor routing decision: CLEAR_OWNERSHIP != CONDUCTOR_BYPASS and FAST_ROUTE != ROUTER_BYPASS. Canonical command /conductor invokes Conductor for task classification, routing, and specialist orchestration.
  3. Specialist Ownership: Domain specialists exclusively own their respective domains:
    • clockwork: Architecture, OOP, layering, refactoring.
    • cloak: UI/UX, accessibility, design patterns.
    • cipher: Security, tenant isolation, access control, secrets review.
    • chronicler: Data persistence, schema, migrations.
    • weaver: Visual modeling, Mermaid/PlantUML diagrams.
    • scribe: Documentation, domain narrative, traceability.
    • overseer: QA, test strategy, validation, release readiness.
    • dagger: Chaos, adversarial, and resilience testing (destructive execution strictly blocked).
    • arbiter: Workflow continuity, validation, and transition governance.
    • the-tuner: Cross-specialist coordination.
  4. Implementation Layer: Ponytail handles focused implementation, strictly keeping code minimal, reversible, and free of over-engineering. Canonical command /ponytail invokes Ponytail for bounded code edits within established architecture.
  5. Simplicity Filter: Caveman ensures the smallest safe change set, avoiding broad refactors during bug fixes.

2. Core Invariants

  • CONDUCTOR != PONYTAIL
  • ROUTING_AUTHORITY != IMPLEMENTATION_AUTHORITY
  • CUSTOM_AGENT_CAPABILITY != ORCHESTRA_ROUTING_AUTHORITY
  • HOST != PROVIDER
  • PROVIDER != SPECIALIST
  • HOST_IDENTITY != AUTHORITY
  • HOST_CAPABILITY != EXECUTION_AUTHORITY
  • PROVIDER_CAPABILITY != PROVIDER_SELECTION_AUTHORITY
  • AVAILABLE_TOOL != PERMISSION
  • INSTALL_SUCCESS != SUPPORTED_INTEGRATION
  • TRANSPORT != WORKFLOW
  • MODEL_SELECTION != GOVERNANCE
  • CONDUCTOR_IS_SOLE_INTERNAL_SPECIALIST_ROUTER
  • CLEAR_OWNERSHIP MAY_ENABLE DIRECT_SINGLE_SPECIALIST_FAST_ROUTE
  • CLEAR_OWNERSHIP != CONDUCTOR_BYPASS
  • FAST_ROUTE != ROUTER_BYPASS
  • UAI_TRANSPORT_SELECTION != AWF_SPECIALIST_ROUTING

3. Code Modification Rules

  1. Inspect relevant files before proposing modifications.
  2. Produce targeted, syntax-correct, and codebase-aware changes with minimal diffs.
  3. Apply persistent project updates only to Git-tracked repo source paths, not .agents/ or generated mirrors.
  4. Run project validations after changes:
    • python scripts/governance_check.py --strict
    • python scripts/preflight_sync_check.py
    • python scripts/validation/validate_architecture_boundaries.py
  5. Do not remove files, rename files, change public APIs, change database schemas, or run destructive commands without explicit user approval.
  6. Keep secrets, tokens, credentials, and private data out of code, logs, and prompt artifacts.

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.