sprint-orchestrator: Command for Claude Code

.claude/commands/orchestrator.md

orchestrator is a command for Claude Code from MarcTorrent/sprint-orchestrator. It costs 26 tokens per session (2,101 once invoked), scanned A, original, MIT.

A command that starts a sprint orchestrator, the agent responsible for dividing sprint tasks into workstreams and merging their changes in order.

In plain words
What is it for?
Use it to analyze sprint files, define workstreams, coordinate agents, and integrate completed work into the develop branch.
Why use it?
It provides a defined process for checking sprint state, handling task dependencies, and coordinating parallel development safely.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is MarcTorrent/sprint-orchestrator's own configuration. It tells Claude Code how to work on sprint-orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sprint-orchestrator configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../worktrees/<workstream-name>.

Reuse

Borrowing it

Nothing to install: this file belongs to MarcTorrent/sprint-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MarcTorrent/sprint-orchestrator/main/.claude/commands/orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/MarcTorrent/sprint-orchestrator

Made for: Claude Code.

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/commands/marctorrent/sprint-orchestrator/orchestrator/github.svg)](https://agentmods.dev/commands/marctorrent/sprint-orchestrator/orchestrator)
Your own site
<a href="https://agentmods.dev/commands/marctorrent/sprint-orchestrator/orchestrator"><img src="https://agentmods.dev/badge/commands/marctorrent/sprint-orchestrator/orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/commands/marctorrent/sprint-orchestrator/orchestrator"><img src="https://agentmods.dev/badge/commands/marctorrent/sprint-orchestrator/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00026 $0.02101
Opus 5 $0.00013 $0.01051
Sonnet 5 $0.00005 $0.00420
Haiku 4.5 $0.00003 $0.00210

Measured 9d ago against content hash 90bd5df63e65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orchestrator 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 9d 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.

.claude/commands/orchestrator.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Orchestrator Mode

You are the SPRINT ORCHESTRATOR for the test-parallel-workflows project. Your role is to coordinate multiple workstreams and integrate them sequentially into develop.

Step 1: Sprint Setup & State Check

1.1 Analyze Sprint and Define Workstreams (if not done)

Your exclusive responsibility: You are the ONLY one who defines workstreams and groups tasks into workstreams. This is a strategic decision that requires understanding task dependencies and parallelization opportunities.

Important: Sprint files generated by /generate-sprint will have tasks with assigned agents, but NO workstreams defined. You must analyze the sprint file and define workstreams.

If workstreams are already defined in sprint file (from manual editing or previous analysis):

pnpm sprint:analyze .claude/backlog/sprint-X-<name>.md

This will parse existing workstreams and create the sprint configuration.

If workstreams are NOT defined (which is the case for files generated by /generate-sprint):

Option A: Interactive Mode (Recommended)

pnpm sprint:analyze .claude/backlog/sprint-X-<name>.md --interactive

This prompts you to:

  1. Review all extracted tasks
  2. Define workstream names (e.g., ui-components, backend-api, testing)
  3. Assign tasks to workstreams
  4. Automatically updates sprint file with workstreams section

Option B: Flag Mode

pnpm sprint:analyze .claude/backlog/sprint-X-<name>.md --workstreams="ui:TASK-001,TASK-002;api:TASK-003,TASK-004"

Option C: Manual Edit Edit the sprint file to add workstreams section manually, then re-run pnpm sprint:analyze.

Workstream Assignment Guidelines:

  • Group related tasks that can be worked on by a single agent
  • Consider dependencies (tasks that depend on each other should be in same workstream or sequential workstreams)
  • Balance workstream sizes (avoid overloading one agent)
  • Name workstreams descriptively (e.g., ui-components, backend-api, infrastructure)

Read the full file on GitHub · 265 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. 9d ago First seen · 265 lines · 26 tokens per session scan A 90bd5df63e65

Subscribe to this mod's changes

orchestrator is a command published in the GitHub repository MarcTorrent/sprint-orchestrator (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 2,101 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 2026-08-31.