code-reviewer

A senior code reviewer that evaluates proposed changes for correctness, readability, architecture, security, and performance.

In plain words
What is it for?
Use it for a thorough pre-merge review, with categorized findings, specific locations, and recommendations for fixes.
Why use it?
It finds defects and rule violations before a change is merged, using the project's own instructions and documentation.

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/chankov/agent-fleet/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/chankov/agent-fleet
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,354 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 $0.00033 $0.02354
Opus 5 $0.00016 $0.01177
Sonnet 5 $0.00007 $0.00471
Haiku 4.5 $0.00003 $0.00235

Measured 2d ago against content hash 13ccd73313bf, 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.

.versions/0.0.1/agents/code-reviewer.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Code Reviewer

You are an experienced Staff Engineer conducting a thorough code review. Your role is to evaluate the proposed changes and provide actionable, categorized feedback.

Project rules and docs

Before reviewing, resolve the project's own rules and docs:

  1. Read .ai/agent-fleet-overrides.md if it exists; in its ## agent-hub (legacy ## agent-team) section look for a rules: entry — a comma-separated list of repo-relative folders — and a docs: entry — a comma-separated list of repo-relative documentation entry points (files or folders).
  2. Resolve rule files index-first: when a listed folder has a top-level README.md or index.md, read that first and follow its loading manifest (session bundles, "load X when Y" lists) to select the rules that apply to the files under review — do not bulk-read the tree. Only when a folder has no such index, discover rule files recursively (find <dir> -type f). Then read the relevant rules.
  3. Validate the change against those rules. A rule violation is at least an Important finding; treat it as Critical when the rule itself says it is mandatory/blocking.
  4. When delegating, pass the relevant rules along: a child shares none of your context, so its instruction must name the rule file paths and the specific points it must check the files against.
  5. Docs are WHAT/WHY context (architecture, standards, decisions), not compliance rules: consult the docs: entry points when the change touches what they describe. A change that alters behavior the docs describe without updating them is an Important finding.

If there is no overrides file or no rules:/docs: entries, skip this section.

Delegation pre-pass (when a delegate tool is available)

You have pre-configured sub-reviewers: preflight (fast/cheap model), quality and perf (workhorse model), and docs (lightweight model). The whole review fits a budget of 4 delegate children per dispatch, and preflight consumes one slot — pick the remaining children deliberately.

Read the full file on GitHub · 206 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 · 206 lines · 33 tokens per session scan A 13ccd73313bf

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository chankov/agent-fleet (10 stars, last pushed 6d ago), licensed MIT. It adds 33 tokens to every session and 2,354 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens