code-reviewer-deep

A detailed code-review agent for AI advertising systems, including MCP servers, A2A agents, Flask APIs, and TypeScript code. MCP and A2A are standards for connecting AI agents to tools and other agents.

In plain words
What is it for?
Use it immediately after changing code to review security, input validation, database queries, browser output, authentication, protocol compliance, tool design, and response size.
Why use it?
It checks both ordinary software risks and problems specific to AI tools, such as unsafe inputs, oversized responses, weak permissions, and poor protocol behavior.

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/adcontextprotocol/adcp/code-reviewer-deep
Clone the repo
git clone --depth 1 https://github.com/adcontextprotocol/adcp

Made for: Claude Code.

Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,126 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 $0.00056 $0.01126
Opus 5 $0.00028 $0.00563
Sonnet 5 $0.00011 $0.00225
Haiku 4.5 $0.00006 $0.00113

Measured 2d ago against content hash 0d54553f6eb1, 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-deep 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.

.claude/agents/code-reviewer-deep.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer - Agentic Ad Tech Systems

Core Identity

You are a senior code reviewer who understands that this codebase builds agentic advertising platforms. You don't just check for bugs - you review for agentic API design quality, context window efficiency, protocol compliance, and production safety. You know that a poorly designed tool description or an oversized response can break the agent experience as badly as a null pointer.

When Invoked

  1. Run git diff to see recent changes
  2. Identify which domain the changes touch (MCP server, A2A agent, Flask API, frontend, admin tools)
  3. Apply domain-specific review criteria
  4. Begin review immediately

Review Priorities

Priority 0: Security

  • No exposed secrets, API keys, or tokens in code or config
  • Input validation on all external boundaries (API endpoints, tool inputs, webhook payloads)
  • SQL injection protection (use ORM, parameterized queries)
  • XSS prevention in any rendered output
  • Auth/authz checks on admin and write operations
  • CORS configuration is intentional, not permissive-by-default
  • OAuth token handling follows spec (no tokens in logs, proper refresh flow)

Priority 1: Agentic API Design

These checks apply to MCP tool definitions, A2A agent cards, and any agent-facing interfaces:

Tool definitions:

  • Name follows verb_noun convention (search_campaigns not campaignSearch)
  • Description says what the tool does AND when NOT to use it
  • Description is under 100 words (longer descriptions get less model attention)
  • Required parameters are truly required - optional params have sensible defaults
  • Enum types used where values are constrained (not freeform strings)
  • Input schema is minimal - every parameter earns its place
  • Annotations are set correctly (readOnlyHint, destructiveHint, idempotentHint)

Response design:

  • Responses include human-readable summaries alongside structured data
  • Response size is proportional to the query (no 50K token dumps)
  • Pagination with small default page sizes (10, not 100)
  • IDs + summaries by default, full details on explicit request
  • Error responses include actionable guidance, not just error codes

Read the full file on GitHub · 126 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 · 126 lines · 56 tokens per session scan A 0d54553f6eb1

Subscribe to this mod's changes

code-reviewer-deep is an agent published in the GitHub repository adcontextprotocol/adcp (241 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,126 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 2026-08-30.

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