spec-review

spec-review is a skill for Claude Code, Codex from Insajin/autopus-adk. It costs 9 tokens per session (1,479 once invoked), scanned A, original, MIT.

A review gate for checking the quality of specification documents with multiple review providers. A specification describes what should be built and how its completion will be judged.

In plain words
What is it for?
Use it to review specification, plan, acceptance, and research documents before implementation.
Why use it?
It prevents incomplete or unsafe specifications from being promoted as approved work and records the review decision.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to review specification, plan, acceptance, and research documents before implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/insajin/autopus-adk/spec-review
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.

Any agent
npx skills add Insajin/autopus-adk --skill spec-review
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

Made for: Claude Code, Codex.

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 spec-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/spec-review/github.svg)](https://agentmods.dev/skills/insajin/autopus-adk/spec-review)
Your own site
<a href="https://agentmods.dev/skills/insajin/autopus-adk/spec-review"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/spec-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/insajin/autopus-adk/spec-review"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/spec-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00009 $0.01479
Opus 5 $0.00005 $0.00740
Sonnet 5 $0.00002 $0.00296
Haiku 4.5 $0.00001 $0.00148

Measured 8d ago against content hash 1bd6b68b7937, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

spec-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 8d 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.

.omp/skills/spec-review/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SPEC Review Gate Skill

A review gate that validates SPEC document quality using multiple providers. Before Step 1, treat .omp/rules/autopus-spec-quality.md as the pre-review self-check that spec-writer should already have applied to spec.md, plan.md, acceptance.md, and research.md.

The CLI writes the authoritative promotion receipt to {SPEC_DIR}/review-receipt.json with schema=spec_review_promotion_receipt.v1. Consumers bind it to the current invocation with run_id and finished_at, then preserve analysis_verdict, gate_status, critical_veto, status_changed, degraded_reasons, and override_applied without recomputing promotion. --allow-degraded is the only operator path that may promote a degraded PASS, and its audit reason remains present after promotion. An unresolved Critical security/correctness finding sets critical_veto=true, keeps gate_status=blocked, and leaves the prior status unchanged.

Review Process

Step 0: spec-writer self-verify

Confirm that the draft went through a first-pass self-check using .omp/rules/autopus-spec-quality.md. Look for observable traces such as research.md's ## Self-Verify Summary or spec.md's ## Open Issues. Also prefer the draft's ## Outcome Lock, ## Completion Debt, ## Evolution Ideas, ## Reviewer Brief, ## Traceability Matrix, and ## Reference Discipline as scope-control evidence: review listed blockers and invariants first, treat Completion Debt as blocking, and treat Evolution Ideas or unrelated deeper-layer suggestions as advisory unless they expose critical/security/data integrity risk. Do not create or request follow-up/sibling SPECs from Evolution Ideas. A sibling SPEC request is valid only when the draft includes a ## Sibling SPEC Decision with an allowed reason and bounded ownership. If the checklist was skipped or obviously not reflected in the draft, call that out as a completeness or style finding before continuing.

Step 1: Load SPEC

Load .autopus/specs/SPEC-{ID}/spec.md and extract requirements.

Read the full file on GitHub · 126 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. 8d ago First seen · 126 lines · 9 tokens per session scan A 1bd6b68b7937

Subscribe to this mod's changes

spec-review is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 1,479 once invoked, about $0.0000 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 2026-09-03.