swarm-dispatch

swarm-dispatch is a skill for Claude Code, Codex from friedbotstudio/baseline. It costs 84 tokens per session (3,640 once invoked), scanned A, original, Apache-2.0.

A workflow runner that sends planned software tasks to separate workers in dependency order, using isolated Git workspaces when available.

In plain words
What is it for?
Use it to execute approved multi-part implementation plans, coordinate parallel workers, and verify their results before merging.
Why use it?
It reduces conflicts when multiple tasks are implemented at the same time and keeps each worker within an assigned set of files.

Skill for Claude CodeCodex

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/friedbotstudio/baseline/swarm-dispatch
Any agent
npx skills add friedbotstudio/baseline --skill swarm-dispatch
Clone the repo
git clone --depth 1 https://github.com/friedbotstudio/baseline

Made for: Claude Code, Codex.

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 swarm-dispatch

README.md
[![agentmods](https://agentmods.dev/badge/skills/friedbotstudio/baseline/swarm-dispatch.svg)](https://agentmods.dev/skills/friedbotstudio/baseline/swarm-dispatch)
Your own site
<a href="https://agentmods.dev/skills/friedbotstudio/baseline/swarm-dispatch"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/swarm-dispatch.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,640 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 $0.00084 $0.03640
Opus 5 $0.00042 $0.01820
Sonnet 5 $0.00017 $0.00728
Haiku 4.5 $0.00008 $0.00364

Measured yesterday against content hash a3e38191fd4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swarm-dispatch 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.

The scan reads SKILL.md. This mod also ships 4 executable files (parse_worker_result.mjs, swarm_merge.mjs, swarm_wave_audit.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/swarm-dispatch/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

swarm-dispatch — wave runner with worktree isolation

Invoked after /swarm-plan + /approve-swarm. The architecture is the user's principle made concrete:

Main context decides. Workers execute.

Per task, before dispatch, you (main context) produce two recipes:

  1. The scenario recipe — exactly which failing tests the worker should write.
  2. The implementation contract — exactly which source files the worker may touch and what behavior they must implement.

The worker's prompt contains both recipes verbatim. The worker invokes Skill(scenario) then Skill(implement) and reports JSON. It makes no design decisions.

Isolation modes

Read project.json → swarm.isolation (default "auto"):

  • "auto" → choose worktree if the project root is inside a git repo (git rev-parse --is-inside-work-tree succeeds), else shared.
  • "worktree" → require a git repo; bail if absent.
  • "shared" → never use worktrees; rely on swarm_boundary_guard for runtime enforcement.

Default path is worktree. The rest of this document describes that mode. The shared fallback is at the end.

Worktree mode = single-wave only (D1). The worktree base commit is chosen by the Agent tool's isolation:"worktree", not by baseline (observed forking from a stale ref on the first real swarm run), and swarm_merge.mjs applies wave output without committing — so a multi-wave worktree plan's wave-N+1 worktrees branch from a base lacking wave-N output. Baseline cannot fix this, only refuse it. Before dispatch, call assertWorktreeWaveSafety({isolation, waves, baselineRef, worktreeBase}) from .claude/skills/swarm-dispatch/worktree-safety.mjs (worktreeBase = git -C <wt> merge-base HEAD <wt-HEAD> once a worktree exists). On ok:false (multi-wave under worktree, or baseline_ref ≠ the worktree's real merge-base), abort and steer the plan to shared isolation — do not run the wave. Multi-wave plans belong in shared mode.

Prereqs (worktree mode)

Read the full file on GitHub · 236 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 236 lines · 84 tokens per session scan A a3e38191fd4c

Subscribe to this mod's changes

swarm-dispatch is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 3,640 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

dispatching-parallel-agents

The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap…

arbiterForge/codeArbiter · 113 tokens

finishing-a-development-branch

The terminal step of /feature and /sprint. Routed to once commit-gate has cleared, to decide the branch's fate — merge via PR, open a PR, or discard. Direct merge to the default branch is forbidden; every change lands through a PR. Under /sprint the skill auto-selects "open PR" and surfaces the merge decision to the…

arbiterForge/codeArbiter · 83 tokens

ca-chore

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

arbiterForge/codeArbiter · 38 tokens

ca-metrics

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

arbiterForge/codeArbiter · 41 tokens

ca-task

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

arbiterForge/codeArbiter · 55 tokens

ca-audit

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

arbiterForge/codeArbiter · 40 tokens