agentleFS
0-CYBERDYNE-SYSTEMS-00-CYBERDYNE-SYSTEMS-0/FFT_nano/skills/runtime/fft-coder-ops/SKILL.md

fft-coder-ops

Skill4 starsChanged 8 months agoMITView on GitHub

Operate FFT_nano coding delegation flows safely using /coder and /coder-plan, preserving main-chat-only policy, request-id tracking, and non-duplicative streaming behavior.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Use this skill when handling coding delegation operations in FFT_nano.

    line 8
  2. Very specific:

    Use for /coder and /coder-plan delegation workflows.

    line 12
  3. Distinctive:

    Use when enforcing main/admin chat boundaries for coding execution.

    line 13
  4. Distinctive:

    Use when tracking delegated run IDs and progress-stream behavior.

    line 14
  5. Distinctive:

    Do not use for non-coding tasks or normal chat replies.

    line 18
  6. Distinctive:

    Do not use when no explicit delegation trigger is present.

    line 19
  7. Distinctive:

    Do not use in non-main chats for delegated execution.

    line 20
  8. Distinctive:

    Never run destructive git commands unless explicitly requested.

    line 24
  9. Distinctive:

    Never bypass main-chat-only coder delegation safety rules.

    line 26
  10. Distinctive:

    Do not add automatic delegation.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

FFT Coder Ops

Use this skill when handling coding delegation operations in FFT_nano.

When to use this skill

  • Use for /coder and /coder-plan delegation workflows.
  • Use when enforcing main/admin chat boundaries for coding execution.
  • Use when tracking delegated run IDs and progress-stream behavior.

When not to use this skill

  • Do not use for non-coding tasks or normal chat replies.
  • Do not use when no explicit delegation trigger is present.
  • Do not use in non-main chats for delegated execution.

Guardrails

  • Never run destructive git commands unless explicitly requested.
  • Preserve unrelated worktree changes.
  • Never bypass main-chat-only coder delegation safety rules.
  • Do not add automatic delegation; delegation remains explicit trigger-based.

Delegation Triggers

Explicit execute:

  • /coder <task>
  • use coding agent
  • use your coding agent skill

Explicit plan-only:

  • /coder-plan <task>

Natural-language coding requests without explicit trigger must not auto-delegate.

Chat Safety Rules

  • Delegation is only available in main/admin chat.
  • Non-main chats may request coding help, but must be handled directly or rejected for delegation.
  • Scheduled tasks must not trigger coder delegation.

Runtime Expectations

  • Execute mode delegates once and returns delegated outcome.
  • Plan mode returns implementation/test plan without direct edits in outer orchestrator turn.
  • Delegation run IDs are generated (coder-<timestamp>-<suffix>) and surfaced in progress messages.
  • Progress streaming should avoid final duplicate full-message sends.

Operator Commands

Main Telegram chat commands:

  • /coder <task>
  • /coder-plan <task>

Alias phrases in main chat:

  • use coding agent
  • use your coding agent skill

Validation Checklist

  • Non-main /coder is rejected with safety message.
  • Main /coder triggers delegation run start message.
  • Main /coder-plan triggers plan run start message.
  • Existing Telegram delegation safety rules remain unchanged.

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.