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.
npx agentmods add commands/kavanaghpatrick/ralph-parallel/dispatchgit clone --depth 1 https://github.com/kavanaghpatrick/ralph-parallelWhat 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.
| Model | Per session | Once 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 |
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.
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 $ARGUMENTS, extract:
- spec-name: Optional spec name (defaults to active spec from
.current-spec) - --max-teammates N: Maximum number of teammates to spawn (default: 4, max: 8)
- --strategy: Isolation strategy -
file-ownership(default) orworktree - --dry-run: Show partition plan without creating team
- --abort: Cancel active dispatch, shut down teammates, clean up state
- --reclaim: Reclaim coordinator ownership for this session
If --abort: skip to Abort Handler section below.
If --reclaim: skip to Reclaim Handler section below.
Step 1: Resolve Spec
1. If spec-name provided: look for specs/$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.Ycheckboxes- 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 Commandssection (older specs won't have it — not blocking) - No test command declared (baseline snapshot will be skipped)
- Tasks missing Files/Verify/Do fields
- Missing
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.
- 2d ago First seen · 327 lines · 0 tokens per session scan A dcc69518376d
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.