orchestrate

orchestrate is a command for coding agents from w00fx/spec-anchored-agentic-development. It costs 91 tokens per session (4,420 once invoked), scanned A, original, MIT.

A command for coordinating GitHub issues through separate worker worktrees, which are independent copies of a repository. It groups related issues into waves and monitors each worker's pull request through checks and reviews.

In plain words
What is it for?
Reading an issue graph, dispatching one autonomous worker per ticket, monitoring CI and review feedback, re-engaging workers when fixes are needed, and waiting for a human to merge.
Why use it?
It organizes dependent issue work and prevents later waves from starting before earlier changes are merged and validated.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/w00fx/spec-anchored-agentic-development/orchestrate
Clone the repo
git clone --depth 1 https://github.com/w00fx/spec-anchored-agentic-development

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/commands/w00fx/spec-anchored-agentic-development/orchestrate.svg)](https://agentmods.dev/commands/w00fx/spec-anchored-agentic-development/orchestrate)
Your own site
<a href="https://agentmods.dev/commands/w00fx/spec-anchored-agentic-development/orchestrate"><img src="https://agentmods.dev/badge/commands/w00fx/spec-anchored-agentic-development/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,420 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00091 $0.04420
Opus 5 $0.00046 $0.02210
Sonnet 5 $0.00018 $0.00884
Haiku 4.5 $0.00009 $0.00442

Measured 3d ago against content hash 5ff5451c3af7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/orchestrate.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate the project in resolution-gated waves

You are the orchestrator, not the implementer. Your own work is mechanical: read the issue graph, compute the wave order, spawn Orca child worktrees with an autonomous agent per ticket, monitor PRs, and advance waves as merges land. Each ticket's code judgment lives inside its worktree agent. You never write ticket code — when a fix is needed, you re-engage the owning worker in its worktree; and you never merge: the human reviews and merges, and their merges gate the next wave.

Phase 0 — Load Orca's mechanism (never from memory)

  1. Resolve the executable once: ORCA_CLI_COMMAND if set; else orca-dev in a dev checkout; else orca-ide on Linux outside an Orca-managed terminal (never bare orca there — GNOME screen reader); else orca. On error, report and stop — no fall-through.
  2. ORCA status --json must succeed.
  3. ORCA skills get orca-cli — read it. The dispatch fabric here is the worktree + terminal layer (create, wait, send, ps, set); its flags evolve with the app, and the loaded guide wins over this file on any conflict. The heavier orchestration layer (Runs, task DAGs, worker_done, decision gates; Settings → Experimental) is not required: the graph lives in GitHub and the PR is the completion signal — one graph, one truth.

Baked-in defaults (do NOT re-ask these)

  • Resolution-gated waves — a ticket starts only after ALL its blockers are resolved: merged to main, a corroborated no-change, or a human graph decision. Every PR targets main; no stacked-branch retargeting. Every wave after the first is cut from fresh, verified origin/main.
  • Workers implement — one autonomous agent per child worktree, born working (worktree create carries agent + prompt in one call; custom models via the terminal recipe in Phase 4); Codex per the declared topology unless --agent overrides. You run from your own slice worktree (<slice>-orchestrator, child of the primary); workers are children of yours — the sidebar mirrors the DAG.
  • CI + review gate — "review-ready" = required checks pass, the applicable-lens review is posted, and no actionable feedback remains. Never merge.
  • The repo's declared interface is the verification truth (check-<capability> / check / golden); the truth layer (specs/**, golden, baseline) is read-only for everyone in the run.
  • Caps — N parallel workers (default 2, never above 3 without instruction); halt on 2 consecutive failures of the same shape.
  • Question policy — workers may ask; business and spec truth is never yours to answer: behavior/criteria/design questions convert the ticket to needs-refinement, release the claim, and go to the human. You answer only mechanical questions, from repo facts.
  • Plan gate modeassisted is the default for a project's first orchestrated run: workers post their plan on the issue and stop until the human replies approved <fingerprint>. autonomous (explicit flag) skips the pause — the quiz-approved ticket is the pre-approved scope. Either way the ticket governs: a plan is a proposal to execute the ticket, never an alternative to it.

Read the full file on GitHub · 338 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 338 lines · 91 tokens per session scan A 5ff5451c3af7

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository w00fx/spec-anchored-agentic-development (5 stars, last pushed 9d ago), licensed MIT. It adds 91 tokens to every session and 4,420 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.