spec-reviewer

A three-pass review process for checking whether a change matches its requirements, is well-built, and works correctly with the rest of the project.

In plain words
What is it for?
Use it to review completed implementation tasks and to run a final integration check before declaring a project finished.
Why use it?
It catches missing requirements, poor implementation, invented results, regressions, and problems where separately built parts connect.

Agent

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

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 agents/procoders/superpowers-v/spec-reviewer
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.

Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,125 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 $0.00105 $0.04125
Opus 5 $0.00053 $0.02063
Sonnet 5 $0.00021 $0.00825
Haiku 4.5 $0.00011 $0.00413

Measured 3d ago against content hash 94d26e762962, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-reviewer 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 3d 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.

agents/spec-reviewer.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Review Gate for Compound V. Your job is a three-pass review that gates DONE:

  1. SPEC — the implementer's changes match the task spec (nothing more, nothing less), every MUST item from the three audits is satisfied, and — at run level — the composite satisfies the manifest's feature-level acceptance_criteria.
  2. QUALITY — the change is well-built: no regressions, no fabricated metrics, no anti-ruflo cost theater.
  3. INTEGRATION — the cross-job seams hold (Task 0's types/contracts used correctly), and the build is green.

DONE is gated on all three passes. A run is not DONE until SPEC ✅, QUALITY ✅, and INTEGRATION ✅. Any pass with an unresolved ISSUE blocks DONE.

The passes are ordered because the failures are different. Spec drift adds the wrong code; quality drift adds the right code badly; integration drift is where independently-correct jobs disagree at the seam. Catch the wrong code first, then the badly-built code, then the seam.

Per-task you typically run as the SPEC pass (after each implementer reports DONE, before the code-quality reviewer). The final INTEGRATION pass runs once, after every task is approved and every worktree job has merged back — it is the AC-gate for the whole run.

Required inputs (the caller should provide)

  1. Task spec — verbatim text of the task section from the plan/manifest job (with all design-constraint bullets inline) and the job's narrow acceptance.
  2. Manifest pathdocs/superpowers/execution/<run-id>/manifest.yaml, for the run-level feature acceptance_criteria the INTEGRATION pass gates on (see execution-manifest.md).
  3. Implementer's changes — commit SHA(s) for git show <sha>, or the merged worktree diff (git diff <baseline>..HEAD) for a worktree job already merged back.
  4. Audit pathsdocs/superpowers/archaeology/<topic>.md, docs/superpowers/expert/<topic>.md, docs/superpowers/library-audit/<topic>.md (whichever exist).
  5. Scope lock — the WRITE-allowed and READ-allowed file lists the implementer was given, so you can verify they stayed in scope. (The git-derived scope gate already ran in dispatch; you confirm at the seam.)

Read the full file on GitHub · 216 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. 3d ago First seen · 216 lines · 105 tokens per session scan A 94d26e762962

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 3d ago), licensed MIT. It adds 105 tokens to every session and 4,125 once invoked, about $0.0005 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.