swarm: Command for Claude Code

.claude/commands/claim.md

claim is a command for Claude Code from swarm-ai-research/swarm. It costs 0 tokens per session (1,020 once invoked), scanned A, original, MIT.

A task-locking command for shared coding work. It records which session owns a task and refuses the task to other sessions until it is released.

In plain words
What is it for?
Use it to claim a task before starting, check whether you still own it, view current claims, or release it when the work is finished or handed off.
Why use it?
It prevents two coding sessions from unknowingly implementing the same task at the same time.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is swarm-ai-research/swarm's own configuration. It tells Claude Code how to work on swarm 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 swarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to swarm-ai-research/swarm. 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/swarm-ai-research/swarm/main/.claude/commands/claim.md
Clone the repo
git clone --depth 1 https://github.com/swarm-ai-research/swarm

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 claim

README.md
[![agentmods](https://agentmods.dev/badge/commands/swarm-ai-research/swarm/claim/github.svg)](https://agentmods.dev/commands/swarm-ai-research/swarm/claim)
Your own site
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/claim"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/claim/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 claim

Your own site · 80×15
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/claim"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,020 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 $0.00000 $0.01020
Opus 5 $0.00000 $0.00510
Sonnet 5 $0.00000 $0.00204
Haiku 4.5 $0.00000 $0.00102

Measured 2d ago against content hash 0e5c6b9d05b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claim 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 2d 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/claim.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/claim

Atomic work-start. Claim a task before doing any work on it — this refuses if another session already holds it, which is the one thing that physically prevents two sessions from building the same feature (the 2026-07-22 duplicate- 7ge5 incident).

Usage

/claim <bead-id> — claim a task and start work /claim status — show what you and every other session currently hold /claim release <bead-id> — release when done (or handing off) /claim check <bead-id> — verify you still hold it (used by the pre-commit gate)

Why this exists

bd update --status=in_progress is advisory — it doesn't stop a second session from picking up the same bead. /claim routes work-start through an atomic claim in the shared cross-worktree coordination DB ($MAIN_REPO_ROOT/runs/runs.db): the first session to claim a task wins, and every other session is refused with the holder's name. No two sessions can hold the same task, so no two sessions can duplicate the work.

Behavior

When you invoke /claim <bead-id>:

  1. Run python -m swarm.agentgit claim claim <bead-id>.
  2. If it prints REFUSED: … already claimed by <session> (exit 2): STOP. Another session is on this. Run /claim status, pick different bd ready work, or coordinate. Do not start the work.
  3. If it prints REFUSED: … declared wards exceed the track's stamped bounds (exit 3): the bead carries a WARDS: stamp from dispatch and what you declared (.agentgit/wards.json, $AGENT_WARDS, or --wards) would widen it — more turns, more depth, a permission the track lacks. Narrow the declaration or take another bead. The claim was not taken. Dry-run with python -m swarm.agentgit wards check <bead-id>.
  4. If it prints CLAIMED … (exit 0): a marker is written to .agentgit/current-claim.json and the bead is set in_progress. Proceed. The marker also holds the effective ward set you run under (track stamp composed with your declaration; the stamp alone if you declared nothing) — including the negative spec the Auditor and retro verify against. The pre-commit hook will verify you still hold it at commit time — a collision there means someone took your task mid-flight.
  5. When the task is shipped (or you hand off), run /claim release <bead-id>.

Read the full file on GitHub · 78 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. 2d ago Changed · +24 lines 0e5c6b9d05b9
  2. 9d ago First seen · 54 lines · 0 tokens per session scan A c0071699a5a2

Subscribe to this mod's changes

claim is a command published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,020 tokens. 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 2026-08-30.