code-reviewer

code-reviewer is an agent for Claude Code from luca-mastrostefano/agent-native-setup. It costs 18 tokens per session (323 once invoked), scanned A, original, MIT.

A code-review agent that examines the current changes against the project’s four execution principles and its documentation rules. It reads the differences made in the repository and reports specific findings.

In plain words
What is it for?
Use it after changing code to review the diff, identify missing edge cases or verification, and report findings with file and line references.
Why use it?
It helps catch unsound assumptions, unnecessary changes, weak tests, misplaced responsibilities, and documentation that no longer matches the code.

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/luca-mastrostefano/agent-native-setup/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/luca-mastrostefano/agent-native-setup

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/luca-mastrostefano/agent-native-setup/code-reviewer.svg)](https://agentmods.dev/agents/luca-mastrostefano/agent-native-setup/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/luca-mastrostefano/agent-native-setup/code-reviewer"><img src="https://agentmods.dev/badge/agents/luca-mastrostefano/agent-native-setup/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 323 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 $0.00018 $0.00323
Opus 5 $0.00009 $0.00161
Sonnet 5 $0.00004 $0.00065
Haiku 4.5 $0.00002 $0.00032

Measured 3d ago against content hash 9fb3fc1de31a, 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 3d 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.md · 25 lines

What it actually says

You review changes for this project. Read the diff (git diff) and judge it against the four principles in the root AGENTS.md:

  1. Think before coding — are assumptions sound and stated?
  2. Simplicity first — is this the minimum code? Flag speculative abstractions.
  3. Surgical changes — does every changed line trace to the task? Flag drive-by refactors and reformatting.
  4. Goal-driven — is the change verified by a test that proves it? Flag tautological or happy-path-only tests, and name the missing edge case (boundary, bad input, error path).
  5. Cohesion & coupling — of this change only: does it add a new, unrelated responsibility to a module, or a new dependency across a boundary? If so, name it and suggest where the new code might live — a suggestion, not a mandate. Never flag a file's pre-existing size or push a refactor of code the change didn't introduce.
  6. Docs in sync — does this change make any doc under docs/ (especially docs/architecture/) or an RFC stale? If so, flag the specific file.

Report findings ordered by severity. Be specific: cite file:line. Prefer a few high-confidence issues over a long list. If it's clean, say so plainly.

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. 3d ago First seen · 25 lines · 18 tokens per session scan A 9fb3fc1de31a

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository luca-mastrostefano/agent-native-setup (5 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 323 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

hive-builder

Honey hive subagent. Makes a small, surgical code change (≤2 files) under the Honey Lever-1 ladder — minimum code that needs to exist, nothing speculative — then returns a compact change-manifest to the orchestrator (Lever 3), not a narrated diff. Use when the orchestrator has a well-scoped edit and wants the result…

Green-PT/honey-for-devs · 90 tokens

hive-scout

Honey hive subagent. Read-only code locator — finds where symbols, callers, configs, or patterns live across the repo and returns the map to the orchestrator as a compact, id-keyed handoff (Honey Lever 3), not prose. Use when the orchestrator needs to locate code without spending main-context tokens reading files.…

Green-PT/honey-for-devs · 76 tokens

implementer

Implements a single task end-to-end in an isolated worktree. Spawned by the orchestrate conductor for each task in a plan.

codecast-sh/codecast · 31 tokens

critic

Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.

codecast-sh/codecast · 28 tokens

momus

Momus is a practical work plan reviewer. Its job is to answer one question.

joeyism/agentget · 0 tokens

hephaestus

Hephaestus is a goal-oriented autonomous executor. Unlike Sisyphus-Junior (which handles delegated atomic tasks), Hephaestus works on complex, multi-step implementations from end to end — exploring the codebase and external resources thoroughly before writing a single line of code.

joeyism/agentget · 0 tokens