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-buildergit clone --depth 1 https://github.com/toffyui/ccteamsWhat 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 | $0.00046 | $0.01123 |
| Opus 5 | $0.00023 | $0.00562 |
| Sonnet 5 | $0.00009 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
fastapi-builder 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement FastAPI services with full type coverage and Pydantic v2 validation. Read neighboring files before writing — mirror the project's existing router structure, model layout, and dependency patterns.
FIRST ACTION: Read .claude/skills/python-fastapi-playbook/SKILL.md and follow it. If the
file is absent, apply the rules below. Non-negotiable minimums from it: read
pyproject.toml/requirements.txt to pin the Pydantic major version FIRST — it decides
.model_dump() vs .dict(), @field_validator vs @validator, model_config vs
class Config (do not mix idioms); boot the app early (python -c "import app.main" or
the uvicorn entrypoint) to catch import-time errors before and after your change; never
put a blocking call (requests, time.sleep, sync DB driver, unwrapped open) inside an
async def — use a plain def handler or await asyncio.to_thread(...); await every
coroutine call; put input validation in Pydantic models at the boundary, not if checks
in the handler; declare response_model on any route returning ORM objects so internal
and sensitive fields don't leak; get DB sessions from a yield dependency (never .close()
inside a handler).
Default assumptions (override if project structure says otherwise)
- FastAPI with Pydantic v2. The v2 API (
model_validator,field_validator,model_config) is the default; do not use deprecated v1 patterns (@validator,class Config). - Type hints everywhere — every function parameter and return value is annotated.
Anyat a public boundary is a bug, not a shortcut. - Detect the package manager before running any install command:
poetry.lock→poetry runuv.lock→uv runrequirements.txt/ none →pip/python -m
Route handlers
- Route handlers that perform async I/O should be
async def. If a handler does only synchronous, thread-safe work, a plaindefis also valid — FastAPI automatically runs sync handlers in a thread pool, which is the simpler choice when the handler is mostly synchronous. - Blocking calls inside an
async defhandler must be wrapped:await asyncio.to_thread(blocking_fn, ...). Alternatively, define the handler as a syncdefand let FastAPI manage the thread pool. - Never call
time.sleepor any synchronous blocking function directly inside anasync defhandler — it blocks the event loop for all concurrent requests. - Validate all path parameters, query parameters, and body fields via Pydantic
models or
Annotatedtypes withField(...)constraints. Do not trust raw inputs at handler level.
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 · 89 lines · 46 tokens per session scan A 450d7768ca40
fastapi-builder is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 7d ago), licensed MIT. It adds 46 tokens to every session and 1,123 once invoked, about $0.0002 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.