review-spec

review-spec is a skill for Claude Code, Codex from Terry-Mao/AICodingFlow. It costs 39 tokens per session (980 once invoked), scanned A, original, MIT.

A workflow for reviewing a GitHub pull request that changes only specification documents, such as product plans or technical designs.

In plain words
What is it for?
It reads saved pull-request snapshots, records findings in review.json, and validates that review output.
Why use it?
It checks document quality against a fixed review contract without modifying the specification files or contacting GitHub.

Skill for Claude CodeCodex

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 skills/terry-mao/aicodingflow/review-spec
Any agent
npx skills add Terry-Mao/AICodingFlow --skill review-spec
Clone the repo
git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow

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 review-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/terry-mao/aicodingflow/review-spec.svg)](https://agentmods.dev/skills/terry-mao/aicodingflow/review-spec)
Your own site
<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/review-spec"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/review-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 980 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 $0.00039 $0.00980
Opus 5 $0.00019 $0.00490
Sonnet 5 $0.00008 $0.00196
Haiku 4.5 $0.00004 $0.00098

Measured 4d ago against content hash 870a947f177f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-spec 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.

.github/skills/review-spec/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-spec

Review one spec-only PR from stable local snapshot files and write the single output artifact review.json.

Required Contract

Read .agents/contracts/review.md first and follow it exactly. That contract is authoritative for snapshot trust, untrusted-input handling, PR_DIFF_V1 targeting, review.json structure, severity labels, suggestion blocks, validator requirements, and GitHub/API boundaries.

Do not run gh, post comments, regenerate snapshots, modify the spec files being reviewed, or modify files other than review.json.

Purpose

Use this skill for PRs whose changed files are all under specs/, including product specs, technical specs, design notes, plans, and similar planning documents. This skill reuses the shared review contract but changes the review lens from code defects to document quality.

Applicability

Before reviewing content, inspect the changed file paths in pr_diff.txt.

If every changed file is under specs/, perform a spec document review.

If any changed file is outside specs/:

  • Do not perform code-level review.
  • Write a valid review.json.
  • Put a top-level body note explaining that the PR is outside spec-only review scope and should use review-pr or be split.
  • Use comments: [] unless there is a spec-document finding that can still be safely attached to a changed specs/ line.

Local Guidance

After applying the shared contract, read .github/skills/review-spec-repo/SKILL.md when it exists and apply any non-conflicting repository-specific guidance.

Always read .github/skills/security-review-spec/SKILL.md and apply it as a non-conflicting supplemental design-level security pass on spec PRs. Fold any security findings into the same review.json; do not emit a separate output.

Review Focus

Prioritize findings that would materially affect implementation, review quality, or the ability to use the specs as source-of-truth planning documents:

  • Completeness: missing goals, non-goals, acceptance criteria, validation plans, edge cases, rollout notes, or open questions required by the issue or PR.
  • Clarity: ambiguous requirements, undefined terms, unclear state transitions, vague validation language, or requirements an implementation agent could reasonably misread.
  • Feasibility: plans that do not fit the current repository structure, permissions, automation boundaries, skill contracts, or validation workflow.
  • Alignment: scope drift, missing issue requirements, invented requirements, or product and technical specs that do not reflect the PR or issue intent.
  • Consistency: contradictions within a spec, between product and tech specs, or between examples, acceptance criteria, and validation steps.

Read the full file on GitHub · 100 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 · 100 lines · 39 tokens per session scan A 870a947f177f

Subscribe to this mod's changes

review-spec is a skill published in the GitHub repository Terry-Mao/AICodingFlow (165 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 980 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens