Destynova2/cli-code-skills / cli-forge-chef
cli-forge-chef
VerifiedGenerate a multi-agent orchestrator for any project using the Brigade de Cuisine pattern: Chef (plans, decides), Sous-Chef (validates, merges), Commis (execute). Clients order via a Menu (PERT), the kitchen delivers Plats (merged features). Creates tmuxinator config, prompts, shared-state memory, quality gates, and permissions. Uses Claude Code Agent Teams (TeamCreate + SendMessage) with visible tmux panes. Use when the user wants to parallelize work across multiple Claude Code agents, orchestrate a multi-agent sprint, or says 'boss', 'multi-agent', 'orchestrate', 'parallelize agents', 'team of claudes', 'sprint multi-agent', 'brigade', 'chef'. Also triggers on 'swarm', 'agent team', 'parallel workers', 'PERT multi-agent'.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 51.4 KB |
| references/anti-patterns-chef.md | markdown | 2.7 KB |
| references/apply-quorum.md | markdown | 9.3 KB |
| references/brigade-setup-worktrees.shexecutable | script | 4.7 KB |
| references/ccheck-prompt-template.md | markdown | 4.2 KB |
| references/chef-prompt-template.md | markdown | 37.6 KB |
| references/conflict-resolution.md | markdown | 10.1 KB |
| references/contre-chef-inter-prompt-template.md | markdown | 8.9 KB |
| references/gotchas-chef.md | markdown | 38.0 KB |
| references/maitre-dhotel.md | markdown | 14.4 KB |
| references/parallel-exploration.md | markdown | 9.1 KB |
| references/permissions-template.md | markdown | 16.7 KB |
| references/pert-computation.md | markdown | 17.5 KB |
| references/quality-gates.md | markdown | 1.9 KB |
| references/raw-tmux-fallback.md | markdown | 3.3 KB |
| references/shared-state-template.md | markdown | 8.4 KB |
| references/simplified-model.md | markdown | 9.8 KB |
| references/sprint-persistence.md | markdown | 7.0 KB |
| references/sprint-report-template.md | markdown | 8.0 KB |
| references/templates.md | markdown | 762 B |
| references/tmuxinator-template.md | markdown | 7.4 KB |
references/raw-tmux-fallback.md
View on GitHub# Fallback — Raw tmux script (no tmuxinator)
Generate this script when `tmuxinator` is absent (air-gapped env, immutable OS without Ruby, etc.).
It reproduces the behavior of the tmuxinator YAML using only `tmux` (POSIX shell).
## When to use it
- `which tmuxinator` fails **AND** the user does not have Ruby available
- Air-gapped env with no access to `gem install`
- The user explicitly asked for "no ruby" or "raw tmux"
## Generation
Generate at `{project}/.claude/scripts/chef-{session}.sh` (chmod +x).
```bash
#!/usr/bin/env bash
# Raw-tmux launcher — fallback when tmuxinator is unavailable
# Generated by cli-forge-chef for session: {session_name}
# Equivalent to ~/.config/tmuxinator/{session_name}.yml
set -euo pipefail
SESSION="{session_name}"
ROOT="{project_path}"
PROMPT="${ROOT}/.claude/prompts/chef-${SESSION}.md"
# --- Pre-flight ---
[ -f "$PROMPT" ] || { echo "FATAL: $PROMPT missing" >&2; exit 1; }
command -v tmux >/dev/null || { echo "FATAL: tmux not installed" >&2; exit 1; }
command -v claude >/dev/null || { echo "FATAL: claude not installed" >&2; exit 1; }
# --- Worktrees (idempotent — G13) ---
{worktree_setup_commands}
# e.g.: (cd "$ROOT" && git worktree add ../project-wt-feature -b feat/feature 2>/dev/null) || true
# --- Kill any stale session ---
tmux kill-session -t "$SESSION" 2>/dev/null || true
# --- Window 1: chef (claude with all required flags — G1, G2, G4, G7) ---
tmux new-session -d -s "$SESSION" -n chef -c "$ROOT"
tmux send-keys -t "${SESSION}:chef" \
"claude --dangerously-skip-permissions --permission-mode bypassPermissions --teammate-mode tmux --append-system-prompt \"\$(cat $PROMPT)\"" \
Enter
# --- Window 2: gate (raw shell — the Sous-Chef sends commands here) ---
tmux new-window -t "$SESSION" -n gate -c "$ROOT"
tmux send-keys -t "${SESSION}:gate" \
'echo "=== GATE — merge, rebase, test, build, push, CI ==="' \
Enter
# --- Auto-kick after 12s (G20) ---
( sleep 12 && tmux send-keys -t "${SESSION}:chef" "Start the sprint." Enter ) &
# --- Attach ---
tmux select-window -t "${SESSION}:chef"
tmux attach-session -t "$SESSION"
# --- Cleanup on detach ---
{worktree_cleanup_commands}
# e.g.: (cd "$ROOT" && git worktree remove ../project-wt-feature 2>/dev/null) || true
```
## Launch
```bash
bash {project}/.claude/scripts/chef-{session}.sh
```
## Differences from tmuxinator
| Aspect | tmuxinator YAML | Raw script |
|--------|-----------------|------------|
| Dependency | Ruby + gem tmuxinator | None (POSIX) |
| Reload config | `tmuxinator start {session}` | Re-run the script |
| Doctor check | `tmuxinator doctor` | Inline pre-flight |
| Worktree cleanup | `on_project_stop` | Trap on exit (not handled — manual) |
| Readability | Declarative YAML | Imperative Bash |
## Limitations
- No hot reload: editing the script = kill-session + restart
- No `on_project_stop` hooks: worktree cleanup has to be done manually if the user kills tmux abruptly
- Keep the script versioned inside the project (`.claude/scripts/`) for reproducibility
## SKILL.md integration
Phase 0.3 prereq check: if `tmuxinator` is missing, DO NOT block. Generate the fallback script and explicitly mention it in the Phase 4 report:
```
tmuxinator missing → raw-tmux fallback generated: {project}/.claude/scripts/chef-{session}.sh
Launch with: bash {project}/.claude/scripts/chef-{session}.sh
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |