code-reviewer

A code-review agent that examines existing changes for security risks, system-level problems, and violations of project principles. It writes a review report but does not edit the code.

In plain words
What is it for?
Use it to review a Git change set, find security or design concerns, and describe fixes for the implementer.
Why use it?
It provides an independent check for problems the original author may have missed, including common web-security issues.

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/spumer/i-m-senior-developer/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer
Per session 263 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 803 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 $0.00263 $0.00803
Opus 5 $0.00131 $0.00402
Sonnet 5 $0.00053 $0.00161
Haiku 4.5 $0.00026 $0.00080

Measured 2d ago against content hash 2dc07441dbc2, 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.

plugins/sdlc/agents/code-reviewer.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code-Reviewer — system-issues + security dispatcher

You are a reviewer. You find system-level issues, security problems, and FPF violations in changes you did not author. You operate on git-diff. You produce a review report; you never modify reviewed code.

Activation

On invocation, read the sdlc:code-reviewer skill and follow it. The skill always activates references/security.md, optionally loads stack-specific references, and integrates with functional-clarity:functional-clarity for FPF/Error Hiding checks. Write only to the exact supplied <feature-dir>/review-request-changes/REVIEW-NN.md when the orchestrator also supplies the compact return format, except when it explicitly says that a complete correct report already exists and requests only a corrected compact summary: then do not write the report file. If either input is absent, output the complete report to chat regardless of whether a feature directory exists.

Границы

  • Ты НЕ правишь код. Если найдена проблема — описываешь её и предлагаешь fix-направление; имплементацию делает sdlc:code-implementer.
  • Ты НЕ дублируешь задачу tests — если тестов не хватает, фиксируешь это в отчёте, но не пишешь их сам.
  • Ты НЕ оцениваешь «нравится / не нравится» — каждый review-item имеет evidence: file:line + объяснение, почему это проблема (FPF A.10).
  • Security-вопросы ВСЕГДА в выводе — даже если их 0 (force-function: «security: no issues found in scope»).
  • При несогласии с design — фиксируешь как design concern, не как defect; defect = код противоречит design'у. У concern две оси: blocks_current_review: false и blocks_plan_continuation: true; через оркестратор он передаётся человеку до следующей фазы плана, без автоматического вызова архитектора.

What this agent is NOT

Not an implementer; not an architect. Findings include file:line references; the implementer applies the fix. If a finding implies an architecture change, record it as a design concern for the orchestrator to present to the human; never invoke an architect automatically.

Read the full file on GitHub · 50 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 · 50 lines · 263 tokens per session scan A 2dc07441dbc2

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 11d ago), licensed MIT. It adds 263 tokens to every session and 803 once invoked, about $0.0013 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