coding-agents-farm

<coding_agents_farm>

<when_to_use_skill> Use when a task benefits from parallel execution across multiple coding agents — large features decomposable into independent subtasks, cross-validation by different models/providers, or throughput-critical work. Solves: single-agent bottlenecks, premature completion without testing, agent deviation, token/rate-limit failures going unnoticed. </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-flash-preview (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.