spec-review

spec-review is a skill for Claude Code, Codex from dapi/claude-code-marketplace. It costs 701 tokens per session (1,521 once invoked), scanned A, original, MIT.

A specification-review router for finding gaps, inconsistencies, and contradictions in requirements. It identifies whether the source is a web page, document, issue, local file, or message text, then invokes the review workflow.

In plain words
What is it for?
Reviewing Google Docs, GitHub issues, Docmost pages, local files, or pasted specifications and requesting the appropriate depth of analysis.
Why use it?
It helps uncover unclear or conflicting requirements before implementation begins.

Skill for Claude CodeCodex

Part of the spec-reviewer plugin — 1 skill, 1 command, 11 agents 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 skills/dapi/claude-code-marketplace/spec-review
Any agent
npx skills add dapi/claude-code-marketplace --skill spec-review
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace

Made for: Claude Code, Codex.

Or install spec-reviewer, the plugin that ships this one along with the rest of its 1 skill, 1 command, 11 agents.

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/dapi/claude-code-marketplace/spec-review.svg)](https://agentmods.dev/skills/dapi/claude-code-marketplace/spec-review)
Your own site
<a href="https://agentmods.dev/skills/dapi/claude-code-marketplace/spec-review"><img src="https://agentmods.dev/badge/skills/dapi/claude-code-marketplace/spec-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 701 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,521 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 $0.00701 $0.01521
Opus 5 $0.00351 $0.00760
Sonnet 5 $0.00140 $0.00304
Haiku 4.5 $0.00070 $0.00152

Measured 4d ago against content hash 3aa3ff701fc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

spec-reviewer/skills/spec-review/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Review Skill

Роутер для ревью спецификаций. Определяет источник и уровень глубины, затем ВЫЗЫВАЕТ команду /spec-review через Skill tool.

КРИТИЧЕСКИ ВАЖНО

Эта skill — роутер. Твоя задача:

  1. Извлечь источник (URL, path, #number) из ОРИГИНАЛЬНОГО сообщения пользователя
  2. Определить уровень глубины (флаги или ключевые слова)
  3. Вызвать Skill tool с skill: "spec-review" и корректным args

НЕ выводи текст описывающий вызов. ВЫПОЛНИ вызов через Skill tool. НЕ теряй URL/path из оригинального сообщения пользователя.

Алгоритм

1. Извлечь источник из сообщения пользователя

Найди в ОРИГИНАЛЬНОМ сообщении пользователя (до загрузки этого скилла) один из:

Тип Паттерн Пример args
Google Doc docs.google.com/document/d/... https://docs.google.com/document/d/1abc123/edit
GitHub Issue github.com/.../issues/N или #N с ревью-контекстом https://github.com/org/repo/issues/42
Docmost https://{domain}/p/{pageId} https://docs.company.com/p/3f6f2b9d
Локальный файл путь к файлу docs/spec.md
Текст в сообщении большой блок текста (>500 символов) (пустая строка)

GitHub Issue: активируй ТОЛЬКО при ревью-контексте (слова: "проверь", "ревью", "review", "analyze", "проанализируй", "спеку", "ТЗ"). Без ревью-контекста — это github-issues или task-routing.

2. Определить уровень глубины

Явные флаги (приоритет):

Флаг Синоним
--quick -q
--standard -s
--deep -d
--exhaustive -e
--no-ask (доп. флаг, совместим с любым уровнем)

Ключевые слова (если нет флага):

  • "быстро", "только критичное", "только блокеры" -> --quick
  • "тщательно", "подробно", "глубоко", "детально" -> --deep
  • "полный аудит", "исчерпывающий", "всё проверить" -> --exhaustive

3. Собрать args и вызвать Skill tool

Формат args: [depth_flag] [--no-ask] <source>

Примеры готовых args:

  • https://github.com/org/repo/issues/42
  • --quick #42
  • --deep docs/spec.md
  • --exhaustive https://docs.google.com/document/d/xxx
  • --no-ask #42
  • (пустая строка, если текст спецификации в сообщении)

Read the full file on GitHub · 120 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 120 lines · 701 tokens per session scan A 3aa3ff701fc3

Subscribe to this mod's changes

spec-review is a skill published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 3d ago), licensed MIT. It adds 701 tokens to every session and 1,521 once invoked, about $0.0035 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