dispatch

A command that analyzes a software specification and divides its tasks among parallel coding agents. It can use file ownership or separate worktrees to organize the work.

In plain words
What is it for?
Use it to dispatch an active specification, limit the number of teammates, choose an isolation strategy, preview the partition plan, abort a dispatch, or reclaim coordination.
Why use it?
It reduces the manual effort of splitting a specification into tasks and coordinating several agents while checking that the task format is valid.

Command

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/kavanaghpatrick/ralph-parallel/dispatch
Clone the repo
git clone --depth 1 https://github.com/kavanaghpatrick/ralph-parallel
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,480 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 $0.00011 $0.03480
Opus 5 $0.00005 $0.01740
Sonnet 5 $0.00002 $0.00696
Haiku 4.5 $0.00001 $0.00348

Measured 2d ago against content hash dcc69518376d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

plugins/ralph-parallel/commands/dispatch.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatch

Orchestrates parallel spec execution via Agent Teams. Scripts handle parsing and partitioning; this command handles team creation and coordination.

Parse Arguments

From $ARGUMENTS, extract:

  • spec-name: Optional spec name (defaults to active spec from .current-spec)
  • --max-teammates N: Maximum number of teammates to spawn (default: 4, max: 8)
  • --strategy: Isolation strategy - file-ownership (default) or worktree
  • --dry-run: Show partition plan without creating team
  • --abort: Cancel active dispatch, shut down teammates, clean up state
  • --reclaim: Reclaim coordinator ownership for this session

If --abort: skip to Abort Handler section below. If --reclaim: skip to Reclaim Handler section below.

Step 1: Resolve Spec

1. If spec-name provided: look for specs/$spec-name/tasks.md
2. If no spec-name: read specs/.current-spec
3. Validate tasks.md exists
4. Read .ralph-state.json — warn if not in execution/tasks phase

Step 1.5: Validate Task Format (via script)

Before partitioning, validate that tasks.md is in the expected format:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/validate-tasks-format.py \
  --tasks-md specs/$specName/tasks.md \
  --check-verify-commands \
  --require-quality-commands

Exit codes:

  • 0: Valid — continue to Step 2
  • 1: File not found or empty — "Run /ralph-specum:tasks to generate task list first."
  • 2: Format errors — display the diagnostic output to the user. The script reports exact line numbers and fix suggestions. Do NOT proceed to Step 2. Common causes:
    • ## Task N: headers instead of - [ ] X.Y checkboxes
    • Verify commands that match build/typecheck but not test (proves compilation, not correctness)
  • 3: Valid with warnings — display warnings, then continue to Step 2. Common warnings:
    • Missing ## Quality Commands section (older specs won't have it — not blocking)
    • No test command declared (baseline snapshot will be skipped)
    • Tasks missing Files/Verify/Do fields

Read the full file on GitHub · 327 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 First seen · 327 lines · 0 tokens per session scan A dcc69518376d

Subscribe to this mod's changes

dispatch is a command published in the GitHub repository kavanaghpatrick/ralph-parallel (7 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 3,480 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.