agentmods.dev

v-review-plan

v-review-plan is a command for coding agents from procoders/superpowers-v. It costs 37 tokens per session (594 once invoked), scanned A, original, MIT.

A command that sends a Compound V project plan to an independent Codex review and then combines the findings with the project's own decision process. Compound V is a workflow for planning and dispatching coding tasks.

In plain words
What is it for?
Use it before dispatching a substantial or risky plan to check its assumptions, scope, and implementation risks.
Why use it?
It adds a second review for plans where security, payments, migrations, architecture, or other risks make missed problems costly.

Command

Part of the superpowers-v plugin — 3 skills, 17 commands, 6 agents, 3 hooks shipped together

not rated 35 5d ago A scan 37 tokens original MIT
View the source file procoders/superpowers-v
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-review-plan
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v

Or install superpowers-v, the plugin that ships this one along with the rest of its 3 skills, 17 commands, 6 agents, 3 hooks.

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 v-review-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/procoders/superpowers-v/v-review-plan.svg)](https://agentmods.dev/commands/procoders/superpowers-v/v-review-plan)
Your own site
<a href="https://agentmods.dev/commands/procoders/superpowers-v/v-review-plan"><img src="https://agentmods.dev/badge/commands/procoders/superpowers-v/v-review-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 594 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 $0.00037 $0.00594
Opus 5 $0.00018 $0.00297
Sonnet 5 $0.00007 $0.00119
Haiku 4.5 $0.00004 $0.00059

Measured 4d ago against content hash d31133f8f06f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

v-review-plan 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 4d 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-review-plan.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running a cross-model plan review on {{args}} — an independent second opinion from a different model family (Codex/GPT), per cross-model-review.md.

Run it on demand, or automatically before dispatch when the project set review.cross_model: true at /v:init Step 3c (read from .claude/compound-v.json). Either way the stakes check below still applies — skip small/mechanical plans.

Steps

  1. Resolve the plan path. Use {{args}}; if empty, list docs/superpowers/plans/*.md and ask which to review.

  2. Stakes check (gating). Confirm this plan warrants a cross-model review (security/auth/payments/migrations, large/coupled partition, architectural change, or the user asked). If it's small/mechanical, say so and recommend skipping — the Opus partition-reviewer + validate-manifest.py already cover it.

  3. Dispatch the read-only Codex reviewer:

    scripts/compound-v-codex-review.sh --plan-file "<plan>" --repo "$PWD" --effort xhigh

    (Add --context-file <audit> for any archaeology/domain/library audits that ground the review.) The model is resolved for codex / tier deep. Codex reads the repo read-only and returns findings JSON per schemas/plan-review.schema.json.

  4. ARBITRATE — you own the decision, Codex is advisory. For EVERY finding, do one of:

    • ACCEPT → the objection is real; note the fix (and apply it / fold it into the plan).
    • OVERRIDE → wrong or already handled; give a one-line rebuttal with the reasoning.

    Then: escalate to the human any critical/high finding you want to OVERRIDE; set the real verdict yourself (Codex's reject may become "proceed with fixes"); and present a short arbitration table (finding → ACCEPT/OVERRIDE → why).

  5. Hand back the arbitrated decision: proceed to dispatch, revise the plan first, or escalate. Do NOT treat Codex's verdict as a hard gate — the deterministic validate-manifest.py is the only hard gate.

Read the full file on GitHub · 34 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. 4d ago First seen · 34 lines · 37 tokens per session scan A d31133f8f06f

Subscribe to this mod's changes

v-review-plan is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 594 once invoked, about $0.0002 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.

Code reviewPlanningclaude-codeclaude-code-plugincode-archaeologyopusparallel-agentssuperpowers
Related

Other commands, from other repositories

gbu-retro

Post-session retrospective — harvest this session's lessons into durable doctrine.

XyndoX/good-bad-ugly · 12 tokens

gbu

Run the tiered multi-agent orchestration loop on a large task.

XyndoX/good-bad-ugly · 13 tokens

doctor

Validate that the Codex-backed workflow fork is installed correctly and the required CLIs are ready.

mzored/superpowers-cc-to-codex · 19 tokens

gbu-audit

Scope-and-rank phase only — a ranked findings list, no delegation.

XyndoX/good-bad-ugly · 14 tokens

gbu-status

Herd the running agents — who's idle, who owes a report, who to verify.

XyndoX/good-bad-ugly · 17 tokens

codex-state

List saved Codex task state for the current workspace so a controller can resume the right thread.

mzored/superpowers-cc-to-codex · 19 tokens