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

fft-setup

Skill4 starsChanged 8 months agoMITView on GitHub

Setup and bootstrap FFT_nano on macOS or Linux, including container runtime checks, dependency install/build, env wiring for Pi provider credentials, and first-run startup validation.

  • Reads credentials
  • Deletes or force-pushes

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 11 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use this skill when the task is to install, bootstrap, or verify FFT_nano runtime setup.

    line 8
  2. Distinctive:

    Use for initial host install/bootstrap and dependency checks.

    line 12
  3. Distinctive:

    Use when configuring provider credentials and runtime environment wiring.

    line 13
  4. Distinctive:

    Use for first-run startup verification on Telegram/WhatsApp paths.

    line 14
  5. Distinctive:

    Do not use for normal day-2 operations or live farm control.

    line 18
  6. Distinctive:

    Do not use for pure code changes unrelated to environment setup.

    line 19
  7. Distinctive:

    Do not use when the user only wants runtime troubleshooting.

    line 20
  8. Distinctive:

    Never run destructive git commands (git reset --hard, git checkout --, force-push) unless explicitly requested.

    line 31
  9. Distinctive:

    Keep admin/delegation operations constrained to the main chat only.

    line 33
  10. Distinctive:

    If WhatsApp is enabled, run one-time auth:

    line 45
  11. Distinctive:

    Ensure Docker daemon is running:

    line 74
  12. Distinctive:

    Ensure daemon is running before start:

    line 83

≈ “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 Setup

Use this skill when the task is to install, bootstrap, or verify FFT_nano runtime setup.

When to use this skill

  • Use for initial host install/bootstrap and dependency checks.
  • Use when configuring provider credentials and runtime environment wiring.
  • Use for first-run startup verification on Telegram/WhatsApp paths.

When not to use this skill

  • Do not use for normal day-2 operations or live farm control.
  • Do not use for pure code changes unrelated to environment setup.
  • Do not use when the user only wants runtime troubleshooting; use debug skill.

Scope

  • Host prerequisites (Node 20+, npm, runtime mode)
  • First-time bootstrap via project scripts
  • Provider/env setup for Pi runtime inside the container
  • First run validation for Telegram and/or WhatsApp

Guardrails

  • Never run destructive git commands (git reset --hard, git checkout --, force-push) unless explicitly requested.
  • Preserve unrelated worktree changes.
  • Keep admin/delegation operations constrained to the main chat only.

Setup Flow

  1. Verify prerequisites:
    • node -v (must be v20+)
    • npm -v
    • Docker mode: docker --version
    • Host mode (advanced): CONTAINER_RUNTIME=host + FFT_NANO_ALLOW_HOST_RUNTIME=1
  2. Bootstrap with project script:
    • ./scripts/setup.sh
  3. Populate .env from .env.example and fill provider vars.
  4. If WhatsApp is enabled, run one-time auth:
    • npm run auth
  5. Start service:
    • Dev: ./scripts/start.sh dev
    • Dev Telegram-only: ./scripts/start.sh dev telegram-only
    • Prod: ./scripts/start.sh start

Provider Wiring (Pi runtime in container)

Preferred variables in .env:

  • PI_API
  • PI_MODEL
  • PI_API_KEY (or provider-specific keys like ZAI_API_KEY, OPENAI_API_KEY, ANTHROPIC_API_KEY)
  • Optional: PI_BASE_URL

Example (Z.AI/GLM):

PI_API=zai
PI_MODEL=glm-4.7
ZAI_API_KEY=replace-me

Platform Notes

macOS

  • Runtime uses Docker by default.
  • Ensure Docker daemon is running:
    • docker info
  • Optional unisolated host runtime requires explicit opt-in:
    • CONTAINER_RUNTIME=host
    • FFT_NANO_ALLOW_HOST_RUNTIME=1

Linux

  • Runtime uses Docker by default.
  • Ensure daemon is running before start:
    • docker info

Setup Verification Checklist

  • npm run typecheck passes.
  • npm test passes.
  • Service starts without startup exceptions.
  • Telegram mode: /status responds.
  • Main chat behavior is correct:
    • main chat responds to normal messages
    • non-main chat requires @FarmFriend (or configured @<ASSISTANT_NAME>)

Farm Mode Handoff

For farm bridge onboarding, use the dedicated dual-mode bootstrap:

  • Demo (simulated telemetry + showcase): ./scripts/farm-bootstrap.sh --mode demo
  • Production (real devices + mapping + validation): ./scripts/farm-bootstrap.sh --mode production

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.