agentleFS
clonable-edenclonable-eden/cekernel/skills/setup/SKILL.md

setup

Skill17 starsChanged 8 months agoMITView on GitHub

Getting Started — Initialize cekernel runtime directory and user profile

  • Reads credentials

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 1 is distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

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

    Use AskUserQuestion to ask both at once:

    line 14
  2. Very specific:

    Read envs/README.md (Read tool) and display the User-configurable Variables table (Variable, Default, Purpose), excluding CEKERNEL_VAR_DIR …

    line 23
  3. Very specific:

    Ask (AskUserQuestion, header "Additional Configuration"): "No, use defaults" → skip to Step 3 / "Yes, customize" → continue.

    line 24
  4. Distinctive:

    After each successful variable, ask (header "More Variables"): "No, continue" → Step 3 / "Yes" → repeat from 3.

    line 30
  5. Very specific:

    Important: write VAR_DIR as an absolute path — tilde is not expanded inside values read by load-env.sh.

    line 56
  6. Very specific:

    Do NOT create or modify the target repo's settings — this is a recommendation only.

    line 68
  7. Very specific:

    Do NOT run sudo at any point — the purpose of this skill is to avoid it via user-local paths.

    line 72
  8. Very specific:

    If ~/.config/cekernel/envs/default.env already exists, show the current content and ask whether to overwrite.

    line 73
  9. Very specific:

    Use $HOME (not ~) inside scripts.

    line 74

“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “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

/setup

Interactive setup for the cekernel runtime environment. Creates the directory structure and writes a user profile to ~/.config/cekernel/envs/default.env.

Workflow

Step 1: Ask CEKERNEL_VAR_DIR and CEKERNEL_BACKEND

Use AskUserQuestion to ask both at once:

  1. Runtime directory (header: "VAR_DIR"): options ~/.local/var/cekernel (Recommended) ("User-local directory. No sudo required.") and /usr/local/var/cekernel ("System-wide directory. May require sudo to create."); "Other" allows a custom path.
  2. Backend (header: "Backend"): options headless (Recommended) ("No terminal required. Runs in the background."), wezterm ("Visualize Workers in WezTerm tabs."), tmux ("Run Workers in tmux sessions.").

Map the answers: the path from the selected label or custom input; the backend name (headless, wezterm, or tmux).

Step 2: Additional variable configuration

  1. Read envs/README.md (Read tool) and display the User-configurable Variables table (Variable, Default, Purpose), excluding CEKERNEL_VAR_DIR and CEKERNEL_BACKEND.
  2. Ask (AskUserQuestion, header "Additional Configuration"): "No, use defaults" → skip to Step 3 / "Yes, customize" → continue.
  3. Accept input via AskUserQuestion with "Other" free-text: "Enter a variable to set (KEY=VALUE format):"
    • Separator normalization: the user may separate key and value with =, :, ;, /, |, or space — replace the first occurrence with = before validation (e.g. CEKERNEL_WORKER_TIMEOUT 1800 → CEKERNEL_WORKER_TIMEOUT=1800).
  4. Validate:
    • The variable name must exist in the User-configurable Variables table; otherwise show an error and ask again.
    • The value must match the "Valid Values" column: "Positive integer" → ^[1-9][0-9]*$; enumerations (e.g. true/false, backend names, none/open/pbcopy) → exact match; "Directory path" / "Any filename" → non-empty string. On failure, show the expected format and ask again.
  5. After each successful variable, ask (header "More Variables"): "No, continue" → Step 3 / "Yes" → repeat from 3.

Step 3: Create directory structure

mkdir -p "${VAR_DIR}/ipc" "${VAR_DIR}/locks" "${VAR_DIR}/logs" "${VAR_DIR}/runners"
if [ ! -f "${VAR_DIR}/schedules.json" ]; then
  echo '[]' > "${VAR_DIR}/schedules.json"
fi

Step 4: Write user profile

mkdir -p "$HOME/.config/cekernel/envs"
cat > "$HOME/.config/cekernel/envs/default.env" <<EOF
# cekernel user profile (generated by /setup)
CEKERNEL_VAR_DIR=${VAR_DIR}
CEKERNEL_BACKEND=${BACKEND}
# Additional variables set during setup:
${ADDITIONAL_VARS}
EOF

${ADDITIONAL_VARS} is the KEY=VALUE lines from Step 2 (one per line); omit the comment and section if none.

Important: write VAR_DIR as an absolute path — tilde is not expanded inside values read by load-env.sh. Expand ~/... to $HOME/... before writing.

Step 5: Summary

Display: runtime directory, backend, count of additional variables (or "none"), profile path — and point to envs/README.md for other options. If the user selected wezterm, also point to config/README.md for the WezTerm plugin installation (read these files to give the actual path relative to the plugin directory).

Also present the recommended target-repo allowlist (ADR-0012 Amendment 4). Workers run headless in the target repository's checkout; without a pre-configured allowlist they may stall silently (blocked) on permission prompts. Recommend that each target repository ships a .claude/settings.json containing a non-empty permissions.allow, e.g.:

{"permissions": {"allow": ["Bash", "Edit", "Write", "Read"]}}

Do NOT create or modify the target repo's settings — this is a recommendation only; permission configuration is the operator's decision (spawn.sh warns at spawn time when it is missing, and --permission-mode acceptEdits is the alternative escape).

Important

  • Do NOT run sudo at any point — the purpose of this skill is to avoid it via user-local paths.
  • If ~/.config/cekernel/envs/default.env already exists, show the current content and ask whether to overwrite.
  • Use $HOME (not ~) inside scripts.

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.