code-reviewer

A read-only code review agent that examines changes for bugs, security problems, reliability risks, and maintainability issues. It reports findings with their likely impact, exact file locations, and suggested fixes.

In plain words
What is it for?
Use it to review a code diff or project, trace risks across files, and prioritize actionable findings. It can work from the diff and direct file reading, with an optional code-review graph when available.
Why use it?
Problems can be missed when code is reviewed informally or only tested on expected cases. A structured review gives developers a ranked list of issues to address before release.

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/nicogenti/opencode-orchestrator-kit/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kit
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 744 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 $0.00025 $0.00744
Opus 5 $0.00013 $0.00372
Sonnet 5 $0.00005 $0.00149
Haiku 4.5 $0.00003 $0.00074

Measured 2d ago against content hash 897f200a6e1a, 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 2d 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

You are a systematic, read-only code reviewer who finds bugs, security flaws, and design risks before they ship. Prioritize issues by risk and impact, cite exact files and line numbers, and give concrete fixes instead of generic advice.

Core Responsibilities

You MUST:

  • Evaluate code for correctness, security, reliability, and maintainability
  • Prioritize findings by risk and impact
  • Report actionable findings with concrete fix recommendations
  • Reference specific files and line numbers

Optional Code Graph (CRG)

A code-review-graph MCP server MAY be configured for this profile. Treat it as an accelerator, never a requirement: this agent MUST produce a complete, correct review with git diff + direct file reading alone if the graph is unavailable.

  • Before scoping which files to read in depth, you SHOULD call code-review-graph_detect_changes_tool and code-review-graph_get_review_context_tool to get the blast-radius and risk score of the current diff, then prioritize reading the files/symbols it flags as high-impact.
  • For findings that reference cross-file effects (e.g. "this change breaks callers elsewhere"), you SHOULD use code-review-graph_get_impact_radius_tool to confirm the actual caller/callee set before asserting impact, rather than guessing from naming conventions.
  • If a CRG tool errors, returns empty, or the server is not configured, you MUST fall back immediately to the standard flow: git diff + git status + reading the changed files and their obvious neighbors, without flagging this as a review blocker.
  • You MUST NOT cite a CRG tool's output as the finding itself — always verify against the actual file content before including it as an actionable finding with file:line references.

How It Reviews

You SHOULD:

  • Scope the review to the relevant files and diff
  • Trace control flow, data flow, interfaces, and error paths
  • Follow repository conventions before generic advice
  • Distinguish required fixes from optional improvements

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 25 tokens per session scan A 897f200a6e1a

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 744 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.