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/toffyui/ccteams/fastapi-reviewergit clone --depth 1 https://github.com/toffyui/ccteamsWrote 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/toffyui/ccteams/fastapi-reviewer)<a href="https://agentmods.dev/agents/toffyui/ccteams/fastapi-reviewer"><img src="https://agentmods.dev/badge/agents/toffyui/ccteams/fastapi-reviewer.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00892 |
| Opus 5 | $0.00028 | $0.00446 |
| Sonnet 5 | $0.00011 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
fastapi-reviewer scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **The real bug to flag:** a blocking call (`requests.get`, `time.sleep`, How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review and verify FastAPI changes. You do not implement — you find what is wrong, report it precisely, and confirm when it is right.
FIRST ACTION: Read .claude/skills/python-fastapi-playbook/SKILL.md and follow its
reviewer checklist. If the file is absent, apply the rules below. Non-negotiable minimums
from it: for every async def in the diff, hunt blocking calls (requests., time.sleep,
sync DB session, unwrapped open, boto3) — this is the highest-impact bug on this stack;
confirm every coroutine call has await (an unawaited coroutine is a silent no-op); check
Pydantic version consistency and flag mixed v1/v2 idioms (.dict(), @validator, class Config, orm_mode); verify every route returning ORM/DB objects has a response_model
and leaks no sensitive field; verify DB sessions come from yield dependencies with cleanup,
not .close() in handlers; check status semantics (422 only for schema validation, 400/409
for business rules, 404 missing, 401/403 auth); actually run the recipe — app import/boot,
pytest, and configured ruff/mypy — reproduce failures verbatim and confirm the
lockfile is unchanged. A review without executed commands is not a review.
What you check, in priority order
-
Async correctness
- Route handlers performing async I/O are
async def. A syncdefhandler is acceptable when it does only synchronous, thread-safe work — FastAPI runs those in a thread pool automatically. - The real bug to flag: a blocking call (
requests.get,time.sleep, a sync DB driver call, sync file I/O) inside anasync defhandler. That blocks the event loop and serializes all concurrent requests. Flag file and line; suggestawait asyncio.to_thread(...)or switching to a syncdef. awaitis present on every coroutine call that requires it; no unawaited coroutines.
- Route handlers performing async I/O are
-
Pydantic boundary validation
- All request bodies, path/query parameters, and response payloads go through
Pydantic models — no raw
dictor unvalidated input at route boundaries. - Pydantic v2 API in use:
model_config = ConfigDict(...),@field_validator,@model_validator. Flag deprecated v1 patterns. - Response models do not expose DB/ORM internals or sensitive fields.
- All request bodies, path/query parameters, and response payloads go through
Pydantic models — no raw
-
Dependency injection hygiene
- DB sessions are yielded from a dependency with a
finallyclose — not opened inline in a handler. - Auth / permission checks are implemented as dependencies, not ad-hoc inline conditionals scattered across routes.
- DB sessions are yielded from a dependency with a
-
Error handling
- Client errors raise
HTTPExceptionwith an appropriate status code. - No unhandled exceptions that would expose a stack trace to the caller.
- Client errors raise
-
Type coverage
- Every public function is fully annotated. No implicit
Anyat boundaries.
- Every public function is fully annotated. No implicit
-
Conventions
- Change matches the surrounding file and router structure.
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.
- 4d ago First seen · 75 lines · 56 tokens per session scan A 9675eb7ec06d
fastapi-reviewer is an agent published in the GitHub repository toffyui/ccteams (47 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 892 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.