orchestrate

orchestrate is a skill for Claude Code, Codex from Everyone-Needs-A-Copilot/claude-copilot. It costs 42 tokens per session (396 once invoked), scanned A, original, MIT.

A workflow for planning and coordinating parallel coding-agent work. It breaks work into streams, checks dependencies and file ownership, and starts subagents only after the user approves delegation.

In plain words
What is it for?
Use it to create a task breakdown, validate stream dependencies, assign disjoint files, launch approved workers, and manage merges.
Why use it?
It reduces conflicting edits and unclear handoffs when several agents work on one project.

Skill for Claude CodeCodex

Part of the claude-copilot plugin — 72 skills, 17 commands, 17 agents, 4 hooks shipped together

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 skills/everyone-needs-a-copilot/claude-copilot/orchestrate
Any agent
npx skills add Everyone-Needs-A-Copilot/claude-copilot --skill orchestrate
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code, Codex.

Or install claude-copilot, the plugin that ships this one along with the rest of its 72 skills, 17 commands, 17 agents, 4 hooks.

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/skills/everyone-needs-a-copilot/claude-copilot/orchestrate.svg)](https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/orchestrate)
Your own site
<a href="https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/orchestrate"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 396 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 5.1 $0.00042 $0.00396
Opus 5 $0.00021 $0.00198
Sonnet 5 $0.00008 $0.00079
Haiku 4.5 $0.00004 $0.00040

Measured today against content hash 8c26c9ae6408, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 today.

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.

plugins/codex-copilot/skills/orchestrate/SKILL.md · 57 lines

What it actually says

Orchestrate

Coordinate parallel work in a Codex-native way.

Boundary

Codex Copilot does not auto-spawn workers unless the user explicitly asks for delegation or parallel execution.

Workflow

  1. Use ta to create a PRD, task breakdown, streams, dependencies, and file ownership.
  2. Validate stream dependencies and file overlap with scripts/orchestrate-validate.py before any parallel work begins.
  3. Use git worktrees only after confirming the branch/worktree plan with the user.
  4. Spawn Codex subagents only when explicitly requested.
  5. Keep write scopes disjoint and route each implementation stream through qa.
  6. Treat merge, cleanup, and removal operations as separate actions requiring explicit current approval when destructive.
  7. For a user-requested cost-capped non-interactive worker, pass --max-budget-usd through tc worker; do not imply that stored metadata enforces a cap unless the installed tc contract says so.

Stream Metadata

Each stream should declare:

{
  "streamId": "Stream-A",
  "streamName": "Foundation",
  "files": ["src/example.ts"],
  "streamDependencies": [],
  "streamPaths": ["src/example/**"],
  "streamTokenBudget": 2500
}

Launch Template

When the user explicitly approves delegation, spawn each stream with:

  • specialist role and skill
  • task id and stream id
  • owned files or path globs
  • forbidden paths
  • expected work product and QA route

Output

  • stream plan
  • dependency graph
  • file ownership map
  • launch instructions or local execution plan
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. today First seen · 57 lines · 42 tokens per session scan A 8c26c9ae6408

Subscribe to this mod's changes

orchestrate is a skill published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 396 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

cadence-first

Meta-orchestrator: assigns skill-chain cadence per block (Tier 1/2/3) via Q1-Q6 rules. Reads target taskblocks + task.md, writes cadence-decisions-{R}.md artifact. Standalone (executor invokes) or Batch (generator hand-off). Use when: deciding cadence for a batch of blocks, generator hand-off from decomposition skills.

bearded-illirian/trailmark · 79 tokens

ship-first

Final task completion protocol: report → user-note → deploy → smoke test → close? → guide? → routing.db → propagate → STATUS → sessions. Invoked from fast-track and pipeline flows after task execution, not directly by the user. Use when: invoked after the execute step of a fast-track or pipeline task.

bearded-illirian/trailmark · 68 tokens

ui-ai-first

Final audit of a large task before closure — finds which operations are available only via code / curl / SQL and decides per each: automate with a skill or AI agent (A) or create a UI task (B). Protects against invisible usability debt. Walks through each implemented block: reads task.md + reports + guides + code →…

bearded-illirian/trailmark · 145 tokens

decision-first

Makes an architectural / project / scope decision using a 5-part model INSTEAD of asking the user. Structure: 🎯 Decision / Why / 🛡 Security / 📈 Scalability / Alternatives / Plain-language analogy. 1 question = 1 atomic artifact. Use when: the agent is about to ask an architectural / scope question…

bearded-illirian/trailmark · 89 tokens

library-first

Mandatory protocol before executing any fast-track task. Analyzes the task, builds a table: what we do / where it comes from / how many lines of code. Principle: maximum reuse of existing libraries and components, minimum new code. Waits for explicit user approval — does nothing until confirmed. Use when: fast-track…

bearded-illirian/trailmark · 77 tokens

fixture-new

Creates a parity fixture — the frozen scenario plus the contract its output must satisfy. Asks which skill and case, what shape the run must produce, and writes input.md and expect.yml. Ends by proving the new fixture actually fails on an empty directory. A fixture that passes when nothing ran is worse than no…

bearded-illirian/trailmark · 122 tokens