review-spec

review-spec is a skill for Claude Code from sergeyklay/.agents. It costs 165 tokens per session (2,431 once invoked), scanned A, original, Apache-2.0.

A pre-implementation review of a software specification or design document. It checks whether the document is clear and complete enough for someone to build safely.

In plain words
What is it for?
Use it to review a feature specification alongside its task or issue, identify what must change, and decide whether development is ready to begin.
Why use it?
It finds ambiguous requirements, missing assumptions, and unaddressed quality concerns before they become implementation defects or production problems.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it to review a feature specification alongside its task or issue, identify what must change, and decide whether development is ready to begin.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sergeyklay/.agents/review-spec
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 sergeyklay/.agents --skill review-spec
Clone the repo
git clone --depth 1 https://github.com/sergeyklay/.agents

Made for: Claude Code.

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/sergeyklay/.agents/review-spec/github.svg)](https://agentmods.dev/skills/sergeyklay/.agents/review-spec)
Your own site
<a href="https://agentmods.dev/skills/sergeyklay/.agents/review-spec"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/review-spec/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 review-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergeyklay/.agents/review-spec"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/review-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 165 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,431 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.
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 $0.00165 $0.02431
Opus 5 $0.00082 $0.01215
Sonnet 5 $0.00033 $0.00486
Haiku 4.5 $0.00016 $0.00243

Measured 7d ago against content hash a3a0b912cd40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 7d 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/skills/review-spec/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.

Specification Architectural Review

You are conducting a deep architectural review of a specification or design document — before implementation begins. You answer one question: is this spec ready to be implemented, and if not, what must change?

A spec is the contract between an architect and an implementer. Every ambiguity, every unstated assumption, every quality-attribute trade-off the spec leaves implicit will surface as a defect during implementation or in production. Your review is the last gate before implementation begins; the cost of catching issues at this stage is orders of magnitude lower than catching them after code is written.

Input

The user provides two arguments:

  1. Task name — a brief description of the feature ("Implement worker attempt function") OR a GitHub issue reference (https://github.com/owner/repo/issues/123, owner/repo#123, #123).
  2. Spec path — a markdown file defining the architecture or design.

If the invoker has already quoted the issue title and body in this prompt (typical when an orchestrator fetched the tracker in an earlier phase and passed the context forward), use those values directly — do not re-fetch. Otherwise, if the task name is a GitHub issue reference, fetch context with gh issue view <ref> --json title,body, and use the fetched title as the task name and the body as additional context. If the argument is plain text and no issue context was provided, treat it as the task name verbatim.

Workflow

The review proceeds in five phases. Each phase has a documented gate that prevents a specific failure mode (ungrounded reviews, missed conventions, ambiguity blindness, severity inflation). Do not skip, merge, or abbreviate any phase.

Copy this checklist into your response and mark items as you complete them:

  • Phase 1 — Resolve task reference
  • Phase 2 — Build project context
  • Phase 3 — Read the specification thoroughly
  • Phase 4 — Evaluate against six dimensions
  • Phase 5 — Compose the review

Read the full file on GitHub · 120 lines

Files

What ships with it

3 files 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. 7d ago Changed · -4 tokens per session a3a0b912cd40
  2. 11d ago First seen · 120 lines · 169 tokens per session scan A af4b1a552fe0

Subscribe to this mod's changes

review-spec is a skill published in the GitHub repository sergeyklay/.agents (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 165 tokens to every session and 2,431 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories