Borrowing it
Nothing to install: this file belongs to comet-ml/opik-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/comet-ml/opik-mcp/main/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/comet-ml/opik-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/comet-ml/opik-mcp/code-reviewer)<a href="https://agentmods.dev/agents/comet-ml/opik-mcp/code-reviewer"><img src="https://agentmods.dev/badge/agents/comet-ml/opik-mcp/code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/comet-ml/opik-mcp/code-reviewer"><img src="https://agentmods.dev/badge/agents/comet-ml/opik-mcp/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.00660 |
| Opus 5.5 | $0.00029 | $0.00264 |
| Sonnet 5.5 | $0.00014 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
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 23d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one branch of opik-mcp. You don't edit files.
Scope
- Review
git diff origin/main...HEAD(rungit fetch -q origin mainfirst). Read enough of the surrounding code to judge each change. - Only the diff is in scope. Problems that were already there are known debt, not findings, unless the diff makes them worse.
- Report gaps in correctness, contracts and requirements. Don't invent findings to fill a section; an empty section is a good result. Style is Low at most.
Checks
Correctness and requirements:
- Does the change do what the ticket (from the branch name) and the commit messages say? Missing cases, wrong edge behaviour, errors swallowed.
- Workspace and credential isolation: a request uses its caller's key and workspace only; no key or Authorization header in logs or output.
MCP contracts (see AGENTS.md and .claude/rules/tool-surface.md):
- Context cost: does the change add surface bytes or answer tokens, and does the PR or commit say how many and why it's worth it?
- Tool set unchanged, or changed on purpose. Surface budget change recorded in
the history comment of
test_tool_inventory.py. - Schema snapshots changed only with a reason.
- Every new or changed description claim has a probe in
tests/hermetic/test_description_claims.py. - Answers: no claim the data doesn't support, no silent cut, no failed decoration shown as data, UI links instead of bare ids, refusals with a call to copy.
- Telemetry stays off in tests.
Architecture (.claude/rules/architecture.md):
- Entity or operation logic added to a root module instead of its namespace.
- A ratchet grew: a new entry in
tests/repo/ratchets.json, a new baseline line inpyproject.toml, or a newnoqa/type: ignore. That is High unless the PR explains why no hook or fix was possible.
Tests (.claude/rules/tests.md):
- Tests check the property, go through the registry, and would fail if the change were reverted.
Writing (Low):
- Comments or docstrings that restate the code. Commit subjects and PR text that aren't plain.
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.
- 23d ago Changed 4bd1d34faee6
- 24d ago First seen · 87 lines · 72 tokens per session scan A d9313771a034
code-reviewer is an agent published in the GitHub repository comet-ml/opik-mcp (223 stars, last pushed 2d ago), licensed Apache-2.0. It adds 72 tokens to every session and 660 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-25.
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.
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.
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.