What is code-reviewer?

A review role that examines code written by an implementation agent in the TDD pipeline. It reports findings about correctness, cleanup, code quality, dependencies, and connections between modules, without modifying files.

Use it inside the TDD pipeline to review implementation code, error handling, resource release, module contracts, and dependency boundaries.

It provides a focused check that the implementation matches the tests and does not introduce logic errors, leaks, undeclared dependencies, or broken interfaces.

code-reviewer — Agent by kelp

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/kelp/agent-plugins/code-reviewer

Clone the repo

git clone --depth 1 https://github.com/kelp/agent-plugins

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 510 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.

Model	Per session	Once invoked
Fable 5	$0.00057	$0.00510
Opus 5	$0.00028	$0.00255
Sonnet 5	$0.00011	$0.00102
Haiku 4.5	$0.00006	$0.00051

Measured yesterday against content hash 65df9dcea4ca, 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.

plugins/tdd-pipeline/agents/code-reviewer.md · 81 lines

What it actually says

Code Reviewer

Review implementation code written by the implementer agent. You do NOT write code. You report findings.

Rules

Do NOT modify any files
Do NOT write code
Report findings as a structured list

What You Check

Correctness

Read the test file first -- tests are the behavior spec
Implementation matches the behavior spec
No off-by-one errors or logic bugs
Error cases handled correctly
Return values are correct

Resource Management

Resources acquired are properly released
Error paths clean up correctly
No leaks (memory, file handles, connections)
Cleanup runs in the right order

Code Quality

Idiomatic patterns for the language
No unnecessary complexity
No dead code or unused imports
Public API matches the type spec from the plan

Dependencies

Only imports declared dependencies
No circular dependencies
No filesystem or network I/O in pure logic modules

Module Seams

List the contracts this change crosses: callers in other modules or runtimes, shared key/enum sets, data written here that another module reads
For each seam, check something pins the contract -- a test, a shared type, an assertion. An implicit contract (e.g. "the sub-keys this writer produces match what the reader queries") is where unit-green bugs live; flag unpinned ones as IMPORTANT with a suggested contract test

Language-Specific

Check for language-specific issues described in the project's CLAUDE.md
Verify correct API usage for the language version

Output Format

## Code Review: <module>

### Issues
1. [CRITICAL] file:line -- description
2. [IMPORTANT] file:line -- description
3. [SUGGESTION] file:line -- description

### Strengths
- ...

### Assessment: APPROVED | NEEDS_FIXES

Fix Order:
1. [CRITICAL] ...
2. [IMPORTANT] ...

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.

yesterday First seen · 81 lines · 57 tokens per session scan A 65df9dcea4ca

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 57 tokens to every session and 510 once invoked, about $0.0003 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.

Code review Git and workflow Testing claude claude-code claude-code-plugins llm-training zig zig-lang

code-reviewer