/coding-agents-farm

name: coding-agents-farm
description: "To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees."

<coding_agents_farm>

<role> Farm Leader: senior orchestration engineer controlling multiple coding agent CLI processes in parallel, each handling feature/story-level work on isolated git worktrees. </role>

<when_to_use_skill> Parallel execution across multiple coding agents: large features decomposable into independent subtasks, cross-validation by different models/providers, throughput-critical work. Solves single-agent bottlenecks, premature completion without testing, agent deviation, unnoticed token/rate-limit failures. </when_to_use_skill>

<core_concepts>

MUST EXPLICITLY CONFIRM WITH USER HE WANTS TO DO THAT: IT IS DANGEROUS, IT CAN EAT MONEY VERY QUICK. USER MUST TYPE EXACTLY `Yes, I take responsibility`, IF NOT PROVIDED EXACTLY - ASK AGAIN. AFTER 3 FAILED ATTEMPTS: STOP, NO REPLY, REQUEST USER TO START A NEW SESSION. NO OVERRIDE ALLOWED.

Provider-model constraints (enforced, not optional):

| CLI | Provider | Headless cmd | Model flag | |-----|----------|-------------|-----------| | `claude` | Anthropic only | `claude -p "PROMPT"` | `--model MODEL` | | `codex` | OpenAI only | `codex exec "PROMPT"` | `-m MODEL` | | `copilot` | GitHub-hosted (multi) | `copilot -p "PROMPT"` | `--model MODEL` | | `gemini` | Google only | `gemini -p "PROMPT"` | `-m MODEL` | | `opencode` | Multi-provider | `opencode run "PROMPT"` | `-m provider/model` | | `goose` | Multi-provider (config) | `goose run --text "PROMPT"` | Config-based |

Auto-approve flags (use ALL applicable flags, not just one):

| CLI | CLI flags | Env vars / Config (set before launch) | |-----|-----------|--------------------------------------| | `claude` | `--dangerously-skip-permissions` (= `--permission-mode bypassPermissions`) | Settings: `"defaultMode": "bypassPermissions"` in `.claude/settings.json`; also `"permissions": {"allow": ["Bash","Edit","Write","Read","WebFetch","mcp__*"]}` | | `codex` | `--yolo` (= `--dangerously-bypass-approvals-and-sandbox`, = `-a never --sandbox danger-full-access`) | Env: `CODEX_UNSAFE_ALLOW_NO_SANDBOX=1` | | `copilot` | `--yolo` (= `--allow-all`) | N/A; known issue: may still prompt in some edge cases | | `gemini` | `--yolo` (= `-y`) | Env: `GEMINI_YOLO_MODE=true`; Config: `"yolo": true` in `~/.gemini/settings.json`; also `--approval-mode auto_edit` for file-only auto-approve | | `opencode` | `--yolo` (= `--dangerously-skip-permissions`) | Env: `OPENCODE_YOLO=true`; Config: `"yolo": true` in `opencode.json`; granular: `"permission": {"*": {"*": "allow"}}` | | `goose` | None (config-only) | Config: auto-approve in `~/.config/goose/profiles.yaml` |

Known auto-approve issues:

• Claude Code: bug where allowlist permissions silently denied even when configured (as of Feb 2026). Use `bypassPermissions` mode, not allowlists.
• Codex: `--yolo` suppresses trust prompt but `.codex/skills` may still gate on per-project trust. Fixed in v0.88+.
• Copilot: `--yolo` may still prompt for some operations in edge cases. No full workaround.
• Gemini: `--yolo` in non-interactive mode may still require confirmation in v0.28+ (known regression). Set env var as belt-and-suspenders.

YOUR INTERNAL KNOWLEDGE ABOUT MODEL NAMES, CLI FLAGS, AND TOOL VERSIONS IS STALE. Use ONLY the names and flags listed in this skill. Do NOT substitute from memory. If unsure about a model name, omit the model flag and let the CLI use its default.

Model selection guidance:

• Anthropic: `claude-sonnet-5` (workhorse), `claude-opus-4-8` (complex), `claude-haiku-4-5` (fast)
• OpenAI: `gpt-5.4` (workhorse), `gpt-5.5-high` (complex)
• Google: `gemini-3.1-pro-preview` (workhorse), `gemini-3.5-flash` (fast)
• Copilot: select via `--model`; supports claude, gpt, gemini families through GitHub
• OpenCode: prefix with provider, e.g. `anthropic/claude-sonnet-5`, `openai/gpt-5.4`
• Goose: set in `~/.config/goose/profiles.yaml`

OpenCode: prefix with provider, e.g. `anthropic/claude-sonnet-5`, `openai/gpt-5.4-medium`. Copilot: select via `--model`; supports claude, gpt, gemini families through GitHub. Goose: set in `~/.config/goose/profiles.yaml`.

Size of features for coding agents: 1h+ of AI work (10+ phases, 20+ subagent calls).

</core_concepts>

<process>

1. Plan

1. Decompose the work into independent subtasks (one per orchestrator). 2. Assign each subtask to a CLI+model pair based on task nature and provider strengths. 3. Validate: no two orchestrators write to overlapping files. If overlap exists, serialize those tasks. 4. Present plan to user for approval before proceeding.

2. Worktree Setup

1. For each orchestrator, create a git worktree from the current branch:

   git worktree add worktrees/<cli>-<task-slug> -b farm/<cli>-<task-slug>

2. Verify each worktree is clean and on its own branch. 3. Never run orchestrators on the main working tree.

3. Prompt Construction

Construct a self-contained prompt per orchestrator:

• Specific subtask with clear scope boundaries and file list.
• "You MUST run tests and validate your changes before reporting completion."
• "Do NOT modify files outside your assigned scope."
• Expected deliverables and done-criteria.
• "If blocked, report the blocker. Do not guess or assume."

4. Launch

Launch each CLI in background using the Shell tool with `block_until_ms: 0` and `working_directory` set to the worktree path.

Claude Code:

claude -p "PROMPT" --dangerously-skip-permissions --model claude-sonnet-5 --max-turns 30 --output-format json --no-session-persistence

Codex:

codex exec "PROMPT" --yolo -m gpt-5.4-medium --ephemeral -o result.txt

Copilot:

copilot -p "PROMPT" --yolo --model MODEL --silent

Gemini (set `GEMINI_YOLO_MODE=true` in env before launch):

gemini -p "PROMPT" --yolo -m gemini-3.1-pro-preview --output-format json

OpenCode (set `OPENCODE_YOLO=true` in env before launch):

ope