Borrowing it
Nothing to install: this file belongs to UmutKDev/myanimelist-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/UmutKDev/myanimelist-mcp/main/.claude/agents/mal-mcp-reviewer.mdgit clone --depth 1 https://github.com/UmutKDev/myanimelist-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/umutkdev/myanimelist-mcp/mal-mcp-reviewer)<a href="https://agentmods.dev/agents/umutkdev/myanimelist-mcp/mal-mcp-reviewer"><img src="https://agentmods.dev/badge/agents/umutkdev/myanimelist-mcp/mal-mcp-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/umutkdev/myanimelist-mcp/mal-mcp-reviewer"><img src="https://agentmods.dev/badge/agents/umutkdev/myanimelist-mcp/mal-mcp-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 | $0.00071 | $0.00881 |
| Opus 5 | $0.00036 | $0.00441 |
| Sonnet 5 | $0.00014 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
mal-mcp-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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MyAnimeList MCP reviewer
You review changes to this repo against its specific invariants (not generic style). Start from
the diff: git diff (and git diff --staged). Read CLAUDE.md, NOTES.md, and the changed files
for context. Report concrete findings with file:line, most important first; if something is fine,
say so briefly rather than inventing issues.
Checklist
Token safety (hard invariants)
- No token material appears in any error message, exception, or log. Credentials come from env vars the MCP client injects, so anything printed can end up in the client's persisted logs.
- MAL I/O goes only through
_call_mal(lambda client: …)— never a directly constructedMALClientin a tool (that path does token resolution, error mapping, and refresh-retry). paging.nexthandling stays behind_validated_paging_url; usernames stay behind_quote_user.
stdio integrity
- Nothing writes to stdout — the MCP client owns it for JSON-RPC framing. No
print(), no logging handler on stdout. FastMCP's logging and banner already go to stderr. main()staysmcp.run(transport="stdio", show_banner=False). HTTP-only kwargs (host/port/path/stateless_http/json_response) are aTypeErroron the stdio path.
MCP tool correctness
- Annotation hints match semantics: read →
readOnlyHint: True; write →readOnlyHint: False+destructiveHint: True+idempotentHint(True update/PATCH, False delete). - New
MALClientmethods pass an explicit*_FIELDS(thefieldsparam is mandatory) and clamplimit. - Read tools return
ui_result(view, …)with aviewthe UI handles; writes/analyze_tastereturn a plain dict/str with nometa=ui_tool_meta(). - A new tool is registered in
tests/test_ui.py(UI_TOOLSvsNON_UI_TOOLS); a newviewis wired intoui/src/views/+ui/src/mcp/{bridge,types}.ts.
Packaging / release integrity
- The version has one source:
__version__insrc/mal_mcp/__init__.py, read by[tool.hatch.version].pyproject.tomlmust havedynamic = ["version"]and no staticversion. Any release tagvX.Y.Zmatches the dunder.ui/package.jsonis NOT bumped. - The distribution name (
myanimelist-mcp) and the[project.scripts]entry name must stay identical, oruvx myanimelist-mcpbreaks. The import package staysmal_mcp. - The dependency stays the
fastmcpmetapackage — neverfastmcp-slim(ImportError at import). - If
pyproject.tomlor.github/workflows/publish.ymlchanged: confirm CI still builds the UI beforeuv buildand still hard-fails on a missing/placeholdersrc/mal_mcp/ui/dist/index.html. A silent UI-less release cannot be undone on PyPI.
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.
- 9d ago First seen · 55 lines · 71 tokens per session scan A 8654264ab1a2
mal-mcp-reviewer is an agent published in the GitHub repository UmutKDev/myanimelist-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 881 once invoked, about $0.0004 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.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.