Dev & Engineering agent-orchestrationcli-toolmulti-agentgit-worktreetask-managementci-cddaemon

ORCH — AI Agent Orchestrator

One CLI to orchestrate them all: run teams of AI agents in parallel on your codebase from isolated git worktrees, hands-free.

FollowSkills review · FSRS-2.0
Use with care
49/ 100 5-point scale 2.5 / 5
1 2 3 4 5 6
1Trust12 / 25 · 2.4/5

SKILL.md claims git-worktree isolation and a mandatory review gate with local state storage and fairly clear data-flow disclosure; however, the default approval-policy is auto, and repository tests show Grok/Antigravity adapters spawn agents with bypassPermissions/--dangerously-skip-permissions; autonomous mode and org deploy auto-generate and execute tasks without mandatory user confirmation or documented rollback, so only a middle score is warranted.

2Reliability9 / 20 · 2.3/5

Docs are internally consistent with a complete CLI reference and troubleshooting guidance (orch doctor, stall timeout, lock protection); the repo has CI workflows and extensive test files. Static review cannot execute anything, the 1954 tests cover the engine rather than the skill's documented CLI key paths, and failure-feedback quality is unverified — capped at 9.

3Adaptability8 / 15 · 2.7/5

Trigger phrases in frontmatter are clear, the Goals-vs-Tasks boundaries are well defined, and adapter scope is declared; but there is no Chinese-language support, and core function depends on overseas CLIs/APIs (Claude, Codex, Cursor) with real mainland-China reachability risk — deducted here.

4Convention10 / 15 · 3.3/5

Good layered structure, MIT license, versioned npm publish flow with changelog extraction, and SECURITY.md; but the skill document itself lacks version/changelog, has no FAQ, includes a hard-coded agent ID example, and maintenance responsibility is only vaguely community-based.

5Effectiveness6 / 15 · 2.0/5

The CLI reference and workflows are detailed and actionable with clear value claims; but static review cannot verify actual outputs, README contains unverified marketing-style examples ($4.20 tokens, 48h MVP), and comparative-benefit evidence is thin — capped at 6.

6Verifiability4 / 10 · 2.0/5

Auditable test code (battle test, PTY e2e, adapter e2e) and CI configs partially corroborate claims; but the skill path's key CLI commands are not directly covered by these tests and no executed reproduction exists — capped at 4.

Evidence confidence:Low Reviewed Sep 10, 2026 Reviewed revision c066dc013e98
Before you use it
  • Default auto approval policy and adapter permission-bypass flags mean agents may execute commands without user confirmation; prefer --approval-policy suggest/manual and review org deploy consequences
  • Core function depends on overseas LLM CLIs/APIs which may be unreachable from mainland China; no Chinese-language support provided
  • The skill's CLI reference is unverified by execution; actual command behavior may differ from docs; publisher identity is unverified
See the full review method →

What does this skill do, and when should you use it?

ORCH (npm package @oxgeneral/orch) is an open-source AI agent runtime that coordinates teams of LLM agents working in parallel on a codebase from your terminal. It combines a CLI and TUI dashboard with automatic goal decomposition, multi-adapter agent management (Claude, Codex, Cursor, OpenCode, Pi, Grok, Antigravity, and any shell command), and a mandatory review state machine that protects your main branch. All state lives in plain YAML/JSON files under .orchestry/ in your project — no database, no cloud. It ships 15 pre-built agent templates and 10 ready-made team templates deployable in one command, aimed at solo founders who want full-team throughput.

Initializes a .orchestry/ project state directory; creates and manages agents with a chosen adapter, model, reasoning effort, approval policy, and workspace mode; adds tasks with priority, file-scope globs, dependencies, and auto-review criteria; hands high-level goals to a lead agent that autonomously decomposes them into tasks; isolates each agent's writes in git worktrees and flows work through todo → in_progress → review → done; supports inter-agent messaging, broadcasts, and a shared context store; provides a TUI dashboard, continuous orchestration via orch run --watch, and a headless daemon (orch serve) with structured JSON logs, pm2/systemd deployment, and a --once CI/CD mode; auto-retries failed tasks and detects stalled (zombie) processes.

  1. A solo founder sets a goal before bed (e.g. implement OAuth2); a CTO agent decomposes it, backend/QA/reviewer agents work in parallel, and pull requests await approval in the morning
  2. A team lead deploys an automated PR review department in one command (orch org deploy pr-review-corp) covering security, performance, and style checks
  3. An engineering team running a large JS-to-TS migration or lifting test coverage from 40% to 80% uses the migration-squad or test-factory templates with iterative, metric-driven goals
  4. Non-engineering workflows: orchestrate writing, data analysis, or sales outreach with content-agency, data-lab, or sales-machine templates, wiring in any CLI tool via the shell adapter
  5. An operator runs agents 24/7 on a server with orch serve under pm2/systemd, piping JSON logs into a monitoring stack
  6. A CI/CD pipeline processes pending tasks with orch serve --once and reads pass/fail from the exit code

What are this skill's strengths and limitations?

Pros
  • Every agent works in an isolated git worktree — main is never touched until you explicitly approve, and a mandatory review gate blocks unreviewed merges
  • Zero infrastructure: no database, no cloud, no Docker; all state is plain YAML/JSON files in .orchestry/
  • Eight adapters (Claude, OpenCode, Codex, Pi, Cursor, Grok, Antigravity, Shell) — the shell adapter turns any CLI tool into a managed agent
  • Ten pre-built org templates deploy a full department in one command, covering engineering, content, data, and sales workflows
  • Auto-retry with exponential backoff, stall detection, and auto-cleanup of stale state after crashes; orch serve offers headless JSON logging and a --once CI/CD mode
  • MIT-licensed, 1954 tests passing, and a layered engine/CLI/TUI architecture you can import as a library
Limitations
  • ~300 MB RAM per concurrent agent (≈2 GB for six agents), which limits scaling on modest hardware
  • Costs depend entirely on the AI APIs you call; the $4.20 example in the README is illustrative, not a guarantee
  • Supported platforms are macOS, Linux, and WSL2 only — native Windows is not listed
  • Agent quality and autonomous goal decomposition depend heavily on model choice and role prompts; the source offers no independent benchmarks
  • The SKILL.md uses the Claude Code-specific allowed-tools frontmatter field, so porting to other Agent Skills clients requires edits

How do you install this skill?

Prerequisites: macOS, Linux, or WSL2 with Node.js >= 20. Install with npm install -g @oxgeneral/orch. Then run orch inside your project directory — it auto-initializes and opens the TUI. Footprint: ~120 MB for ORCH plus roughly 300 MB RAM per concurrent agent process. Run orch doctor to diagnose problems. Note: the repository does not document a separate installation path for the Skill file itself; per the README, the /orch skill becomes automatically available in Claude Code after install.

How do you use this skill?

Typical flow: 1) orch init --name "my-project"; 2) pick agents with orch agent shop, or deploy a whole team with orch org deploy startup-mvp --goal "..."; 3) add work with orch task add "Fix login crash" -d "..." --scope "src/auth/**" -p 1, or create a goal with orch goal add and let the lead agent decompose it; 4) start orchestration with orch run --all --watch or inspect via orch tui; 5) approve or reject tasks in review with orch task approve/reject; 6) always pass -- when parsing output programmatically. In Claude Code, type /orch deploy a team to refactor the auth module and add tests to drive everything in natural language.

How does this skill compare with similar options?

The README contrasts ORCH with Paperclip: Paperclip requires PostgreSQL, a web server, and cloud setup, while ORCH needs only npm install — the same zero-human-company vision, but terminal-first, file-based, zero-infrastructure, and MIT licensed.

FAQ

What system and memory do I need?
Minimum: macOS/Linux/WSL2, 2 cores, 4 GB RAM, 300 MB disk, Node.js >= 20 for 1-2 agents; a full 6-agent department recommends 4+ cores and 8 GB RAM. Budget ~300 MB per agent process plus ~120 MB for ORCH itself.
Will agents mess up my codebase?
No. Each agent works in an isolated git worktree on its own branch, main is untouched until you approve and merge, the state machine enforces a review step, and scope-overlap detection prevents conflicts before they happen.
What does it cost?
ORCH itself is free and MIT-licensed; you pay only for the AI APIs you already use (Claude, Codex, etc.). The TUI shows token costs per agent per run in real time — the README's example of 5 agents and 6 tasks came to $4.20.
Can it run 24/7 on a server?
Yes. orch serve runs as a headless daemon with structured JSON logs, deployable via pm2 or systemd. It supports graceful shutdown on SIGINT/SIGTERM and enforces a single orchestrator per project via the .orchestry/orchestry.lock lock file.

Related skills