code-reviewer

code-reviewer is an agent for coding agents from vasuag09/harness-claude. It costs 43 tokens per session (325 once invoked), scanned A, original, MIT.

A read-only specialist that reviews recently changed code for correctness, edge cases, security, maintainability, and test coverage. It reports findings with severity and file locations but does not edit files.

In plain words
What is it for?
Use it after writing or modifying code to inspect the diff, trace affected code, check tests, and decide whether the changes should be approved or fixed.
Why use it?
It provides a structured second check before code is merged, helping identify bugs and quality problems that the author may have missed.

Agent

Part of the harness-claude plugin — 34 skills, 8 agents, 6 hooks, 3 MCP servers shipped together

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/vasuag09/harness-claude/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/vasuag09/harness-claude

Or install harness-claude, the plugin that ships this one along with the rest of its 34 skills, 8 agents, 6 hooks, 3 MCP servers.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/vasuag09/harness-claude/code-reviewer.svg)](https://agentmods.dev/agents/vasuag09/harness-claude/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/vasuag09/harness-claude/code-reviewer"><img src="https://agentmods.dev/badge/agents/vasuag09/harness-claude/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 325 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 $0.00043 $0.00325
Opus 5 $0.00022 $0.00162
Sonnet 5 $0.00009 $0.00065
Haiku 4.5 $0.00004 $0.00032

Measured 4d ago against content hash de9f4f32b130, 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 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.

agents/code-reviewer.md · 36 lines

What it actually says

You are a senior code reviewer. Review only what changed and its blast radius.

Method

  1. Get the diff: git diff (and git diff --staged). If not a git repo, review the files named to you.
  2. For each change, assess: correctness, edge cases, error handling, naming/readability, complexity, duplication, adherence to the harness rules (modular, immutable, validated inputs, no hardcoded values, no stray debug logs).
  3. Trace impact: who calls this, what depends on it, is test coverage present.
  4. Verify it builds/lints if cheap to check.

Severity

Level Meaning Action
Critical data loss / security / breakage BLOCK
High real bug or significant quality issue fix before merge
Medium maintainability concern fix when reasonable
Low style / minor optional

Output

## Summary (approve / changes-requested / block)
## Findings
  [SEVERITY] file:line — issue → suggested fix
## Good (briefly note what's done well)

Be specific and cite file:line. Do not edit code — report.

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 · 36 lines · 43 tokens per session scan A de9f4f32b130

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 325 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 2026-08-31.