spec-review

spec-review is a skill for Claude Code from adamdaw/claude-code-skills. It costs 85 tokens per session (2,313 once invoked), scanned A, original, MIT.

A cold review of a GitHub work-item issue as a software specification, also called a Gate-1 spec review. A fresh reviewer checks whether the issue clearly and faithfully describes the required work, without building or changing code.

In plain words
What is it for?
Use it before implementation when a GitHub issue serves as the software design document. The review reads the published issue and reports findings against the supplied requirements and project constitution.
Why use it?
It separates specification review from the context that created the issue, making missing or ambiguous requirements easier to spot. It prevents implementation from starting with an unchecked design document.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit Use it before implementation when a GitHub issue serves as the software design document. The review reads the published issue and reports findings against the supplied requirements and project constitution.

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

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 spec-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamdaw/claude-code-skills/spec-review.svg)](https://agentmods.dev/skills/adamdaw/claude-code-skills/spec-review)
Your own site
<a href="https://agentmods.dev/skills/adamdaw/claude-code-skills/spec-review"><img src="https://agentmods.dev/badge/skills/adamdaw/claude-code-skills/spec-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,313 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 $0.00085 $0.02313
Opus 5 $0.00043 $0.01156
Sonnet 5 $0.00017 $0.00463
Haiku 4.5 $0.00009 $0.00231

Measured 8d ago against content hash 78889beec1e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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.

skills/spec-review/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec review (Gate 1)

Runs one cold pass over a GitHub work-item issue treated as the Software Design Document. The reviewer is a fresh subagent invocation; it reads the published issue body and reports findings. Nothing is built.

Throughout, the Architect means the human who owns the spec and declares the gate green.

Why a subagent and not this session

The session that authored the spec cannot review it. A fresh invocation is the structural independence reset — a fresh window resets memory, but a separate invocation is what establishes production independence. Never review a spec you wrote in the same context.

Inputs the reviewer gets, and nothing else

  1. The issue number and the repo (owner/name).
  2. The tracker ticket ID, so it can read the SRS. This gate checks that the SDD faithfully encodes the SRS, so withholding the SRS makes that uncheckable — and invites the reviewer to demand a Requirements section the house SDD skeleton deliberately does not have. The SRS is a source artifact, not deliberation.
  3. The path to CONSTITUTION.md in the local checkout. If that checkout is a stale mirror, tell the reviewer to read it from origin/main instead.
  4. The prompt below, verbatim.

It fetches both bodies itself. Do not paste them in, do not summarise them, and do not mention what you think is wrong with either.

Never pass prior-pass findings, your own reasoning, or the ticket's internal rationale. Those are the deliberation record. Feeding any of them back means the pass returns your own conclusions instead of an independent read.

Where the record lives

Keep two files per ticket, wherever your team keeps its work-item records:

  • work-item.md — the spec body. The authoring surface.
  • spec-review.md — every pass appended under a ## Pass N heading, with the disposition written under each finding.

Edit work-item.md, then push it. Never edit the issue body on GitHub directly. One direction only is what keeps the two from drifting.

Read the full file on GitHub · 212 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 · 212 lines · 85 tokens per session scan A 78889beec1e1

Subscribe to this mod's changes

spec-review is a skill published in the GitHub repository adamdaw/claude-code-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 85 tokens to every session and 2,313 once invoked, about $0.0004 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.