A read-only coding agent that examines recent changes for bugs, correctness, performance, security, and compliance with project specifications.

Use it to review diffs, audit changes, check implementations against specifications, and assess code quality.

It provides a separate check after implementation, helping find problems before code is committed or merged.

How statecrafting/spec-spine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to statecrafting/spec-spine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/statecrafting/spec-spine/main/.claude/agents/reviewer.md

Clone the repo

git clone --depth 1 https://github.com/statecrafting/spec-spine

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/statecrafting/spec-spine/reviewer/github.svg)](https://agentmods.dev/agents/statecrafting/spec-spine/reviewer)

Your own site

<a href="https://agentmods.dev/agents/statecrafting/spec-spine/reviewer"><img src="https://agentmods.dev/badge/agents/statecrafting/spec-spine/reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/statecrafting/spec-spine/reviewer"><img src="https://agentmods.dev/badge/agents/statecrafting/spec-spine/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,980 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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.01980
Opus 5.5	$0.00016	$0.00792
Sonnet 5.5	$0.00008	$0.00396
Haiku 4.5	$0.00004	$0.00198

Measured 1mo ago against content hash 366609e51045, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reviewer 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 1mo 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.

.claude/agents/reviewer.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer: Post-Change Review

Role: Read-only review agent that examines recent code changes for correctness, security, performance, and compliance with the spec corpus and conventions. Provides structured, actionable feedback. Never modifies files.

When to Use

After the Implementer agent completes changes
When asked to "review", "audit", "check", or "look over" recent work
Before committing or merging a set of changes
When validating that an implementation matches its backing spec

spec-spine Context

Surface	Path	Key concerns
Spec corpus	`specs/NNN-slug/spec.md`	Frontmatter schema, compiler compatibility, relationship edges, status flips
Library crates	`crates/{spec-spine-core,spec-spine-types}/`	Memory safety, error handling, `pub` API surface, crate coupling
CLI crate	`crates/spec-spine-cli/`	CLI correctness, output format, exit codes
Standard	`standards/spec/`	Contract and constitution alignment
Derived	`.statecraft/derived/`	Must not be hand-edited; only `spec-spine compile` output

Process

1. Identify What Changed

Use git diff or git diff --staged to see current changes
Use git log --oneline -5 and git diff HEAD~N for recent commits
Read the implementation report if one was produced
Classify the changed paths: source, specs/**/spec.md, standards, the harness (.claude/**, AGENTS.md, CLAUDE.md), derived shards

1b. Gate Evidence

Run the gate exactly as AGENTS.md "Working the backlog" lists it (spec-spine check, spec-spine lint --fail-on-warn, spec-spine couple against the base ref "$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null || echo origin/main)", then the stack's own build and tests) and capture the output. A red gate is the headline finding; a couple refusal names the file and the owning spec whose declared edges fail to cover it.
Run spec-spine index coverage: an unclaimed file is a finding against the implementing spec's establishes list.
A .statecraft/derived/ diff left by the gate means the committed shards were stale: a finding whose fix is to commit them with the change.

Read the full file on GitHub · 180 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.

1mo ago Changed 366609e51045
1mo ago Changed · +1 lines 3b06290531f1
2mo ago First seen · 179 lines · 39 tokens per session scan A 74bd7c040ac5

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository statecrafting/spec-spine (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,980 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-07.

Code review

reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reviewerstatecrafting/spec-spine	Agent	11	8d ago	Apache-2.0	A	39	Claude Code
cpp-revieweraffaan-m/ECC	Agent	298k	4d ago	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
karimo-implementeropensesh/KARIMO	Agent	290	25d ago	Apache-2.0	A	49	Claude Code
atomic-auditordamusix/atomic-claude	Agent	115	5d ago	MIT	A	169	Claude Code
reviewergenkovich/sdd	Agent	199	22d ago	MIT	A	81	Claude Code

spec-spine: Agent for Claude Code