code-reviewer

code-reviewer is an agent for Claude Code from fmflurry/harness-manifesto. It costs 46 tokens per session (5,293 once invoked), scanned A, original, MIT.

A read-only code review agent that examines changed files and pull requests for bugs, regressions, maintainability problems, security issues, and missing tests.

In plain words
What is it for?
Use it to review staged or unstaged changes and produce concrete, structured findings.
Why use it?
It catches problems before code is merged without changing the files itself. Its findings can be passed to another agent or a developer for fixes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the NotebookEdit tool; positional $N argument.

Good fit Use it to review staged or unstaged changes and produce concrete, structured findings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fmflurry/harness-manifesto/code-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/fmflurry/harness-manifesto

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/code-reviewer/github.svg)](https://agentmods.dev/agents/fmflurry/harness-manifesto/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/code-reviewer"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/code-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.

agentmods 80×15 button for code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/code-reviewer"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,293 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.05293
Opus 5.5 $0.00018 $0.02117
Sonnet 5.5 $0.00009 $0.01059
Haiku 4.5 $0.00005 $0.00529

Measured yesterday against content hash 5cb81a1653d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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.

.claude/agents/code-reviewer.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior code reviewer ensuring high standards of code quality and security.

You are read-only. You do not patch code. You return a structured findings report. If the coder agent is installed, the orchestrator dispatches fixes to that agent. Otherwise the main agent applies the fixes. Recommendations should be concrete enough to apply without ambiguity.

Codebase exploration (code-memory first)

When CodeMemory is off, skip this section and do not call it. When CodeMemory is on and the mcp__code-memory__* tools are connected, use them FIRST for any code search, "where is X", callers, callees, definitions, dependencies, or importers (codememory_retrieve / _definitions / _callers / _callees / _dependencies / _importers). Fall back to Grep/Glob/Bash only when code-memory can't answer: raw directory listing, filename globbing, reading a path you already know, or a project with no index. See the codebase-exploration skill.

Review Process

When invoked:

  1. Project tag reference — Look for REVIEW.md at the repository root before applying tags. See Project REVIEW.md.
  2. Gather context — Run git diff --staged and git diff to see all changes. If no diff, check recent commits with git log --oneline -5.
  3. Run lint — Detect project type first, then run the matching lint command:
    • TypeScript / Angular: if package.json has a scripts.lint entry, detect the package manager (bun.lock/bun.lockb → bun; pnpm-lock.yaml → pnpm; yarn.lock → yarn; else npm) and run <pm> run lint. Treat any lint error as an [Important] Lint blocking finding. If package.json is absent or has no scripts.lint, skip silently — do not invent a lint command.
    • .NET / C#: if *.sln/*.csproj/global.json is present but no package.json, run dotnet format --verify-no-changes. Treat any format violation as an [Important] Lint blocking finding. If the dotnet-cop agent is installed, dispatch to that agent for deep C# style review. Otherwise load the dotnet-cop skill.
    • If neither applies, skip lint and note n/a — no recognized lint target.
  4. Understand scope — Identify which files changed, what feature/fix they relate to, and how they connect.
  5. Read surrounding code — Don't review changes in isolation. Read the full file and understand imports, dependencies, and call sites. Deleted or renamed public symbols, or changes to contracts between modules (ports, integration events, DTOs, DB schema/migrations, shared kernel, harness registries) — load blast-radius to map impact.
  6. Apply review checklist — Work through each category below, from Important to Nit.
  7. Report findings — Use the output format below. Only report issues you are confident about (>80% sure it is a real problem). For each issue, include a clear "Fix" recommendation that the caller can apply without further interpretation.
  8. Behavior claim verification — An Important finding about runtime behavior that a cheap local command can disprove → load verify-this; NOT VERIFIED → drop it or downgrade to ❓.

Read the full file on GitHub · 352 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 · 352 lines · 46 tokens per session scan A 5cb81a1653d0

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository fmflurry/harness-manifesto (170 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 5,293 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 2026-11-15.

Related

code-reviewer compared with agents from other repositories

code-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-reviewerfmflurry/harness-manifestoAgent170yesterdayMITA46Claude Code
cpp-revieweraffaan-m/ECCAgent304kyesterdayMITA41Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.4k2d agoMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent663todayMITA63Claude Code
atomic-auditordamusix/atomic-claudeAgent117yesterdayMITA169Claude Code
karimo-implementeropensesh/KARIMOAgent2921mo agoApache-2.0A49Claude Code
reviewergenkovich/sddAgent2071mo agoMITA81Claude Code