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.
npx agentmods add agents/adcontextprotocol/adcp/code-reviewer-deepgit clone --depth 1 https://github.com/adcontextprotocol/adcpWhat 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.
| Model | Per session | Once 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 |
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.
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
- Run
git diffto see recent changes - Identify which domain the changes touch (MCP server, A2A agent, Flask API, frontend, admin tools)
- Apply domain-specific review criteria
- 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_nounconvention (search_campaignsnotcampaignSearch) - 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
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.
- 2d ago First seen · 126 lines · 56 tokens per session scan A 0d54553f6eb1
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.