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/procoders/superpowers-v/v-pr-reviewgit clone --depth 1 https://github.com/procoders/superpowers-vWrote 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.
[](https://agentmods.dev/commands/procoders/superpowers-v/v-pr-review)<a href="https://agentmods.dev/commands/procoders/superpowers-v/v-pr-review"><img src="https://agentmods.dev/badge/commands/procoders/superpowers-v/v-pr-review.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00071 | $0.00426 |
| Opus 5 | $0.00036 | $0.00213 |
| Sonnet 5 | $0.00014 | $0.00085 |
| Haiku 4.5 | $0.00007 | $0.00043 |
Grade A, and why
v-pr-review 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.
What it actually says
You are running a deep PR/MR code review on {{args}} — a pull/merge request URL or number, or, if empty, the current branch against its base.
Invoke the pr-review skill and follow it exactly. The skill is review-only: it never edits, commits, pushes, or merges code.
Steps
- Resolve the target. Use
{{args}}as the PR/MR URL or number. If empty, review the current branch against its base. The skill auto-detects the host — GitHub (gh), GitLab (glab), or a hostless local diff. - Run the pr-review skill end-to-end: build shared understanding of the change's intent, then hunt bugs and edge cases along the two deliberately separate axes — Standards (does the code follow this repo's documented conventions?) ⊥ Spec (does it faithfully implement the originating spec/issue?) — run as context-isolated sub-agents. Promote real unknowns to Open Questions for the author. Every finding gets a verdict + confidence.
- Hand back the triaged findings table. Never modify the reviewed code — if the user asks for a fix mid-review, stop and confirm they want to leave the review first.
Notes
- Review-only — no edits, commits, pushes, or merges (skill Prime Directive 1).
- Full behavior — exploration checklist, review domains, findings format, and comment-posting — lives in
skills/pr-review/SKILL.mdand itsreferences/.
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.
- 4d ago First seen · 19 lines · 71 tokens per session scan A e4e853df7224
v-pr-review is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 5d ago), licensed MIT. It adds 71 tokens to every session and 426 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.
Other commands, from other repositories
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
gbu
Run the tiered multi-agent orchestration loop on a large task.
doctor
Validate that the Codex-backed workflow fork is installed correctly and the required CLIs are ready.
gbu-audit
Scope-and-rank phase only — a ranked findings list, no delegation.
gbu-status
Herd the running agents — who's idle, who owes a report, who to verify.
codex-state
List saved Codex task state for the current workspace so a controller can resume the right thread.