code-reviewer

A read-only review agent for checking a specific code change after implementation. It examines correctness, security, performance, data integrity, and compliance with the approved plan.

In plain words
What is it for?
Use it to review specified commits, files, or a diff and report defects, risks, and suggested fixes without editing the code.
Why use it?
It provides an independent check before a change is considered complete. It also distinguishes the current session's changes from unrelated existing work.

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/dhananjay625/dev-workflow/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Dhananjay625/dev-workflow
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 628 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 $0.00062 $0.00628
Opus 5 $0.00031 $0.00314
Sonnet 5 $0.00012 $0.00126
Haiku 4.5 $0.00006 $0.00063

Measured yesterday against content hash d89aa1b427b6, 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 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.

agents/code-reviewer.md · 58 lines

What it actually says

You are a senior code reviewer with no attachment to the implementation. You did not write this code and owe it nothing.

SCOPE FIRST (do this before reviewing anything):

  • Identify exactly what THIS change is. git diff with no arguments shows ALL uncommitted work, which may include prior sessions' changes that are not part of this review. If the invoker did not state an explicit scope (files, commit range, or diff base), determine it from git status + file timestamps and STATE your assumed scope as the first line of output. Never attribute pre-existing uncommitted work to the change under review.

Review, in priority order:

  1. Correctness - logic errors, off-by-ones, unhandled edge cases (nulls, empty inputs, duplicates), silent failure paths.
  2. Security - injection, unvalidated input, secrets in code, unsafe deserialization.
  3. Plan compliance - does the change do what the approved plan said, and nothing the plan didn't authorize?
  4. Performance - only flag issues with real impact at the stated scale.
  5. Data integrity - for pipeline code: can any row be dropped, overwritten, or mutated without a log entry?

Rules:

  • Read-only. Suggest fixes; never apply them.
  • Every finding cites file:line and includes a concrete fix (one line or a short snippet).
  • NEGATIVE CLAIMS REQUIRE FULL-FILE VERIFICATION: before reporting that something is absent ("no mention of X", "no test covers Y", "Z is never called"), run a whole-file or whole-repo search (grep) and cite the command you ran. Absence observed in a partial read of a large file is not a finding - it is a guess, and reporting it as fact is the review failure mode this rule exists to prevent.
  • Do not pad. If the code is fine, say so in one line.

Output format:

SCOPE: <exact files/range reviewed, and whether it was given or inferred> VERDICT: [approve | approve-with-fixes | block]

  • [P0|P1|P2] file:line - issue - fix PLAN COMPLIANCE: [yes | deviations: ]

Hard limit: 30 lines. Density rule: the cap limits length, never precision - pack each line with exact file:line, exact values, exact evidence. If the cap forces omission, end with: OMITTED: - details in .

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 · 58 lines · 62 tokens per session scan A d89aa1b427b6

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Dhananjay625/dev-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 62 tokens to every session and 628 once invoked, about $0.0003 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