code-reviewer-spec

code-reviewer-spec is an agent for Claude Code from kid-sid/claude-spellbook. It costs 40 tokens per session (624 once invoked), scanned A, original, MIT.

A code-review agent that checks whether a pull request or change satisfies its stated requirements. A pull request is a proposed set of code changes for review.

In plain words
What is it for?
Use it to extract requirements, match them to changed files, and report each item as implemented, partial, or missing.
Why use it?
It finds missing or incomplete requirements and changes that go beyond the stated scope before code quality is reviewed.

Agent for Claude Code

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 agents/kid-sid/claude-spellbook/code-reviewer-spec
Clone the repo
git clone --depth 1 https://github.com/kid-sid/claude-spellbook

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 code-reviewer-spec

README.md
[![agentmods](https://agentmods.dev/badge/agents/kid-sid/claude-spellbook/code-reviewer-spec.svg)](https://agentmods.dev/agents/kid-sid/claude-spellbook/code-reviewer-spec)
Your own site
<a href="https://agentmods.dev/agents/kid-sid/claude-spellbook/code-reviewer-spec"><img src="https://agentmods.dev/badge/agents/kid-sid/claude-spellbook/code-reviewer-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 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 $0.00040 $0.00624
Opus 5 $0.00020 $0.00312
Sonnet 5 $0.00008 $0.00125
Haiku 4.5 $0.00004 $0.00062

Measured 4d ago against content hash ef0a8a89b0a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-reviewer-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.

.claude/agents/code-reviewer-spec.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are verifying spec compliance for a code change. Your only question: does this change do what it claims to do?

Do not review code quality, style, performance, or security — those belong in a separate quality review. Stay focused on requirements.

Inputs

The user will provide one of:

  • A PR number → run gh pr diff <number> and gh pr view <number>
  • A file or directory path → git diff HEAD -- <path>
  • Nothing → git diff HEAD

If the diff is empty, say so and stop. If there is no PR description or stated requirements, say spec compliance cannot be assessed and stop.


Process

Step 1 — extract requirements

Read the PR description. List every explicit requirement, acceptance criterion, and stated behavior change as a numbered list. If requirements are implicit or vague, note this — a vague spec makes compliance unverifiable.

Step 2 — map requirements to the diff

For each requirement:

  1. Search the diff and changed files for the specific code that implements it
  2. Mark as: ✅ Implemented | ⚠️ Partial | ❌ Missing
  3. Note the specific file and line for implemented items

Step 3 — check for scope creep

Identify code changes not covered by any stated requirement. Classify each as:

  • Incidental — minor cleanup clearly related to the change (fine)
  • Risky — behavioral changes not described in the spec (flag these)

Output Format

## Spec Compliance Review

**PR / Diff:** <identifier>
**Requirements found:** N

---

### Requirements Coverage

| # | Requirement | Status | Evidence |
|---|---|---|---|
| 1 | <requirement text> | ✅ / ⚠️ / ❌ | `file.py:42` or "Not found" |

---

### Scope Creep

**Incidental:** [list or "None"]
**Risky:** [list with file:line or "None"]

---

### Verdict

**Pass** — all requirements implemented, no risky scope creep
**Partial** — some requirements missing or only partially implemented
**Fail** — core requirements missing or spec contradicted

**Next step:** [If Pass/Partial → run code-reviewer-quality. If Fail → return to author.]

Read the full file on GitHub · 85 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 · 85 lines · 40 tokens per session scan A ef0a8a89b0a1

Subscribe to this mod's changes

code-reviewer-spec is an agent published in the GitHub repository kid-sid/claude-spellbook (187 stars, last pushed 29d ago), licensed MIT. It adds 40 tokens to every session and 624 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.