orchestrate

orchestrate is a command for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. It costs 15 tokens per session (1,305 once invoked), scanned A, original, MIT.

A command for setting up parallel streams of work for native task agents. It can create a product requirements document and tasks, prepare separate worktrees, show progress, and merge completed work back into the main branch.

In plain words
What is it for?
Use it to generate planned tasks, start parallel worktrees, monitor streams, and merge finished changes.
Why use it?
It organizes independent work so multiple tasks can proceed while checking dependencies and possible conflicts before merging.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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 commands/everyone-needs-a-copilot/claude-copilot/orchestrate
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

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/commands/everyone-needs-a-copilot/claude-copilot/orchestrate.svg)](https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/orchestrate)
Your own site
<a href="https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/orchestrate"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,305 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 $0.00015 $0.01305
Opus 5 $0.00008 $0.00652
Sonnet 5 $0.00003 $0.00261
Haiku 4.5 $0.00002 $0.00130

Measured yesterday against content hash d088e64cb3ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 yesterday.

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.

.claude/commands/orchestrate.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate Command

Scaffolding layer for parallel streams. Agent dispatch is handled by the harness, not by this command.

/orchestrate generate  # Create PRD + stream tasks via @agent-ta
/orchestrate start     # Validate streams, check conflicts, create worktrees, print dispatch cmds
/orchestrate status    # Show stream progress + live sessions
/orchestrate merge     # Merge completed worktrees back to main branch

generate (default if no subcommand)

Creates PRD and tasks with stream metadata. Prompt user for feature description if not provided.

  1. Invoke @agent-ta to design architecture and return structured JSON:
{
  "prd": { "title": "...", "description": "...", "content": "# PRD..." },
  "tasks": [{
    "title": "...", "description": "...",
    "metadata": {
      "streamId": "Stream-A", "streamName": "Foundation",
      "files": ["src/auth.ts"], "dependencies": []
    }
  }]
}
  1. Parse JSON, validate (no cycles, at least one task with dependencies: [])
  2. Persist real rows for start: tc prd create --title "..." --description "..." --json (capture <prd-id>); per unique streamId, tc stream create --name "<streamName>" --prd <prd-id> --json (capture the numeric id); then per task, tc task create --title "..." --prd <prd-id> --stream <numeric-id> --description "..." --metadata '<json>' --json. Skipping --stream/--metadata leaves tc stream conflicts and tc task list --stream <id> empty.
  3. Display plan summary and ask user to approve

start

Validates streams, checks for real file conflicts, creates an isolated git worktree per ready stream, and prints exact dispatch commands (claude --bg or tc worker).

  1. tc stream list --json -- stop if no streams (tell user to run generate first)
  2. Preflight: confirm tc is on PATH, you're inside a git repo, and the working tree is clean
  3. tc stream conflicts --json (hard precondition) -- non-zero exit means a file is claimed by multiple streams. Report the conflicts; stop before creating worktrees.
  4. For each stream whose dependencies are all satisfied, create an isolated worktree:
    git worktree add .worktrees/<stream-id> -b stream/<stream-id>
    
  5. Print one dispatch command per ready stream; each agent works in .worktrees/<stream-id> on that stream's tasks (tc task list --stream <stream-id> --json):

Read the full file on GitHub · 132 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. yesterday First seen · 132 lines · 15 tokens per session scan A d088e64cb3ec

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,305 once invoked, about $0.0001 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 commands, from other repositories

analytics

/analytics Show full analytics dashboard /analytics top Top 10 most-used agents /analytics failures Show agents with highest failure rates /analytics timeline Show invocation timeline (last 7 days) /analytics agent Show stats for a specific agent /analytics trends Show improving vs degrading agents over time…

samibs/skillfoundry · 0 tokens

feature

Role: Per-feature quality pipeline that takes a story or feature description from zero to a committed, documented, tested, and evaluated implementation. No stage is skipped. No commit happens without the evaluator's approval.

samibs/skillfoundry · 0 tokens

security-scanner

Security scanner specialized in detecting AI-generated code vulnerabilities using comprehensive anti-pattern databases. You are methodical, thorough, and uncompromising -- every vulnerability is documented, traced, and given a concrete fix.

samibs/skillfoundry · 0 tokens

data-architect

You are a rigorous data architect. You design schemas that scale, optimize queries that crawl, and normalize (or denormalize) with surgical precision. You do not accept "we'll optimize later" or "it works in dev" database design.

samibs/skillfoundry · 0 tokens

explain

/explain Explain the last agent action (quick mode) /explain --verbose Full trace with file changes and decision rationale /explain --story STORY-XXX All actions for a story in chronological order /explain --agent Last action by a specific agent /explain --session All actions from a specific session /explain --diff…

samibs/skillfoundry · 0 tokens

gohm

Persona: You are the Knowledge Harvester -- you extract signal from noise, turning session work into durable organizational memory. Reflection Protocol: See agents/reflection-protocol.md for reflection requirements.

samibs/skillfoundry · 0 tokens