v-dispatch

A command for executing an approved Compound V plan, manifest, or run ID across multiple backends, with review and scope checks.

In plain words
What is it for?
It helps dispatch a prepared development plan, run an existing execution manifest, or start a run by its ID, including a serial first task followed by parallel batches.
Why use it?
It removes much of the manual coordination needed to send independent implementation tasks to several agents while keeping the planned order and file boundaries.

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/procoders/superpowers-v/v-dispatch
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,351 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 $0.00083 $0.01351
Opus 5 $0.00042 $0.00675
Sonnet 5 $0.00017 $0.00270
Haiku 4.5 $0.00008 $0.00135

Measured 2d ago against content hash 59d552f2dcbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

v-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.

commands/v-dispatch.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are about to execute Phase 3 of Compound V — batched parallel multi-backend dispatch — on {{args}}.

This replaces the default Superpowers subagent-driven-development sequential-implementer pattern with parallel batches (4–6 implementers per message) on Opus by default, Sonnet only where the routing policy's justification holds, and Codex for large isolated jobs — each job dispatched through backend-launcher and gated by the file-scope check on return.

{{args}} is accepted in three backward-compatible forms — the dispatcher detects which:

{{args}} is… Action
a plan path (docs/superpowers/plans/…md) materialize the manifest first (Phase 2 → manifest.yaml + state.json in a new run dir), then dispatch. This is the 0.1.x contract the plan-saved-nudge hook and current users rely on — it still works.
a manifest path (…/execution/<run-id>/manifest.yaml) dispatch it directly (already materialized).
a run-id (a dir name under docs/superpowers/execution/) resolve to that run's manifest.yaml and dispatch directly.

Steps

  1. Resolve {{args}}.

    • If {{args}} is empty, list plans in docs/superpowers/plans/ and runs in docs/superpowers/execution/, and ask which to dispatch.
    • If {{args}} is a run-id or a manifest path, load that run's manifest.yaml. Skip to step 3 (already materialized).
    • If {{args}} is a plan path, verify it exists, then materialize per /v:orchestrate: apply routing-policy.md, write manifest.yaml + initial state.json into docs/superpowers/execution/<run-id>/ (schema: execution-manifest.md; run-dir + state shape: state-machine.md), then continue.
  2. Validate the materialized manifest (only for the plan-path branch). Pick the validator mode by manifest kind (CR5-1): if manifest.yaml carries a fast_path block, validate it in pre-dispatch mode; a legacy (plan-based) manifest carries no such block and is validated mode-lessly, as before — a mode-less fast_path manifest is fail-closed rejected:

    # legacy manifest (no fast_path block):
    python3 scripts/compound-v-validate-manifest.py docs/superpowers/execution/<run-id>/manifest.yaml
    # fast_path manifest (v2.9 pre-eval-backed):
    python3 scripts/compound-v-validate-manifest.py docs/superpowers/execution/<run-id>/manifest.yaml \
      --mode pre-dispatch --repo-root <repo>
    

    Non-zero exit ⇒ fix the manifest and re-run; do not dispatch a manifest the validator rejects. (A plan-path materialization always yields a legacy manifest; the fast_path branch matters when {{args}} is a manifest/run-id that resolves to a pre-eval-backed run — and the partition reviewer in step 3 re-runs the validator with the same mode rule.)

  3. Run the partition reviewer first (Iron Rule #4: no execution without a verified Partition Map):

    • Dispatch compound-v:partition-reviewer with the plan and the manifest (it runs compound-v-validate-manifest.py as its deterministic backing gate, then verifies disjointness + invariants).
    • If verdict is FAILSTOP. Surface the failure to the user. Do not dispatch implementers.
    • If verdict is PASS → continue.
  4. Dispatch the parallel dispatcher:

    • Dispatch compound-v:parallel-dispatcher with:
      • the manifest path (and run dir),
      • the partition-review verdict (PASS),
      • the audit paths: docs/superpowers/{archaeology,expert,library-audit}/<topic>.md.
    • The dispatcher handles Task 0 serially, then the parallel batches (honoring depends_on / run / max_parallel), routing each job to its backend via backend-launcher. After every job it runs the scope gate (git diff --name-onlyls-files --others vs write_allowed): a BLOCKED job HALTS the run and is never merged. It updates state.json after every phase, then runs the collector and the three-pass Review Gate (AC-gated).

Read the full file on GitHub · 56 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 · 56 lines · 83 tokens per session scan A 59d552f2dcbe

Subscribe to this mod's changes

v-dispatch is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 1,351 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 2026-08-30.