v-orchestrate

A command that turns an approved development plan into a machine-readable execution manifest and starting state file. It prepares the run but does not start it.

In plain words
What is it for?
Use it after a verified plan, or an accepted fast-path evaluation, when you need to prepare files for a later dispatch step.
Why use it?
It creates a reviewable contract for the dispatcher, so the planned jobs and routing can be inspected or edited before execution.

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-orchestrate
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,343 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 $0.00072 $0.02343
Opus 5 $0.00036 $0.01171
Sonnet 5 $0.00014 $0.00469
Haiku 4.5 $0.00007 $0.00234

Measured 2d ago against content hash edcda01c1ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

v-orchestrate 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-orchestrate.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running /v:orchestrate — the materialize step of Compound V. You turn a verified plan into the machine-readable contract the dispatcher runs: a manifest.yaml plus an initial state.json in a fresh run directory. This command does not dispatch — it produces the manifest and stops, so the user (or /v:dispatch) can inspect or edit it first.

The argument is {{args}}. It is normally a plan path. It may instead be an accepted fast-path pre-eval — a pre_eval_id (YYYY-MM-DDThhmmssZ-<slug>-<nonce>) or a path to docs/superpowers/pre-eval/<pre_eval_id>.json whose decision is FASTPATH_ELIGIBLE — in which case take Step 0 and stop.

The manifest schema and rules are defined in skills/compound-v/execution-manifest.md; the routing decisions come from skills/compound-v/routing-policy.md; the run-dir layout and state.json shape come from skills/compound-v/state-machine.md. Read those — they are the authority; this command is the procedure.

Steps

  1. Fast-path branch (accepted pre-eval → committed single-job run). If {{args}} resolves to an accepted FASTPATH_ELIGIBLE pre-eval record (a pre_eval_id, or a docs/superpowers/pre-eval/<pre_eval_id>.json path with decision: FASTPATH_ELIGIBLE), do not run the plan-based flow below — the fast path has no full plan and no three audits. Instead delegate to the deterministic materializer, which runs the authoritative Phase-M lifecycle (mint a deterministic run-id from pre_eval_id → copy the pinned taxonomy snapshot into the run → write spec/plan stubs, block-YAML audit skip-records, the single-job fast_path manifest with the review declaration only, and the captured implementer prompt → commit all artifacts except state.jsonappend + commit the bind eventcommit state.json at FASTPATH_DISPATCHED LAST). It also runs the validator in --mode pre-dispatch as an in-code gate before binding, so a manifest the validator would reject never reaches dispatch.

    python3 scripts/compound-v-fastpath-materialize.py materialize \
      --repo . --pre-eval-id <pre_eval_id> [--prompt-file <captured-implementer-prompt>]
    

    The materializer is idempotent + crash-consistent: a committed state.json at FASTPATH_DISPATCHED ⇒ the bind is already durable ⇒ the run is complete (re-running is a no-op); a run interrupted before state.json is rebuilt deterministically (same pre_eval_id → same run-id; an existing child is discovered before another is minted). It fails closed — a tampered record (its localization.resolved_paths[0] disagreeing with the committed localization artifact, a non-FASTPATH_ELIGIBLE decision, or a taxonomy snapshot whose bytes don't content-address to the record's taxonomy_digest) is rejected before any write or commit. Report the run-id and the next step (/v:dispatch <run-id>), then stop — Steps 1-9 below do not apply.

  2. Resolve the plan. If {{args}} is empty, list the plans in docs/superpowers/plans/ and ask the user which to materialize. If the named plan path does not exist, stop and say so.

  3. Read the plan and its pre-flight audits. Extract:

    • the feature title and feature-level Acceptance Criteria (from the spec the plan targets),
    • the verified Partition Map (the disjoint write-paths per task),
    • the three audit paths (docs/superpowers/{archaeology,expert,library-audit}/<topic>.md). If the plan has no Partition Map, stop — this plan is not Compound-V-ready; route it through Phase 2 (skills/compound-v/phase-2-disjoint-partitioning.md) first.
  4. Choose the run-id. Convention: YYYY-MM-DD-<slug> (the slug from the plan/feature). The run dir is docs/superpowers/execution/<run-id>/. Create it (and jobs/ + results/ subdirs).

  5. Apply the routing policy (routing-policy.md) to each partition entry. For every job set backend · model · isolation · run from its type, honoring the active stance in .claude/compound-v.json (Balanced default; Claude-only when Codex is absent). Consult docs/superpowers/memory/routing-lessons.md — a recorded lesson overrides the table default for that pattern.

Read the full file on GitHub · 65 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 · 65 lines · 72 tokens per session scan A edcda01c1ef4

Subscribe to this mod's changes

v-orchestrate is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 2,343 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.