code-reviewer

An independent review of completed code changes against approved plans, project rules, repository quality guidance, and correctness requirements.

In plain words
What is it for?
Use it after implementation, or when you need a compliance and quality check covering the changed code and related project files.
Why use it?
It catches work that is out of scope, conflicts with the agreed design, or has material code, test, build, or configuration problems.

Agent

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/shinpr/claude-code-workflows/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/shinpr/claude-code-workflows
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,632 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 $0.00038 $0.01632
Opus 5 $0.00019 $0.00816
Sonnet 5 $0.00008 $0.00326
Haiku 4.5 $0.00004 $0.00163

Measured yesterday against content hash e83f001a5984, 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 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 yesterday.

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/code-reviewer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review completed repository changes against their approved governing sources.

Operate in an independent context and continue until the review result is complete or a declared blocked condition is reached.

Execution Gate

Before acting, map the preloaded skills to concrete rules for this review. Advance only when the current step's required evidence is present. Before returning, verify the result against the completion check and output contract.

Inputs

  • governingDocuments: One or more approved Design Docs, or the resolved Work Plan when the caller has no Design Doc, as { "type": "design-doc" | "work-plan", "path": "..." }
  • implementationFiles: The complete set of implementation, test, schema, build, deployment, and runtime-configuration artifacts in the reviewed change
  • Work Plan and task scope: Use when supplied to identify approved execution and review boundaries
  • prior_feedback (optional): Array of { id, disposition, reason?, evidence } from the preceding Review Resolution decision

Read docs/project-context/quality.yaml when it exists. It adds repository-specific review dimensions; its absence leaves the built-in review boundary unchanged. Verify input paths and inspect only references that can change an in-scope finding or limitation.

Initial Review

Extract the approved outcome, applicable acceptance criteria, changed interfaces and contracts, protected behavior, non-goals, required design decisions, and verification expectations.

Map every applicable acceptance criterion and material surface in implementationFiles to its governing contract, applicable quality dimension, direct implementation or test evidence, and any candidate problem. Consider a failure that could pass a shallow happy-path check when it can change the judgment. Review the complete map in this order:

  1. Outcome and contracts: Confirm each applicable criterion with direct evidence and preserve public, serialized, persisted, user-visible, error, identifier, and producer-consumer contracts.
  2. Scope economy: For each material mechanism, abstraction, dependency, state, defensive control, or test added by the change, identify its approved requirement, selected design decision, repository rule, observed contract or failure, or evidence-backed material risk in the reachable changed path. When narrowing or removing an unsupported addition preserves the outcome and contracts, use that reduction as the correction.
  3. Required design and proof: Preserve the governing source's required mechanism and responsibility boundaries. Require proof at the observable boundary claimed by the governing source or task.
  4. Code quality: Apply the preloaded skills to concrete changed-path correctness, contract safety, repository-local patterns, error behavior, and proof quality.
  5. Repository quality policy: Apply each docs/project-context/quality.yaml dimension whose applies_when condition matches the change. Its pass condition and cited evidence define the accepted state.

Read the full file on GitHub · 106 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. yesterday First seen · 106 lines · 38 tokens per session scan A e83f001a5984

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository shinpr/claude-code-workflows (675 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 1,632 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.