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 skills/ccplugins/awesome-claude-code-plugins/fastapi-appnpx skills add ccplugins/awesome-claude-code-plugins --skill fastapi-appgit clone --depth 1 https://github.com/ccplugins/awesome-claude-code-pluginsWhat 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 | $0.00103 | $0.01071 |
| Opus 5 | $0.00051 | $0.00535 |
| Sonnet 5 | $0.00021 | $0.00214 |
| Haiku 4.5 | $0.00010 | $0.00107 |
Grade A, and why
fastapi-app 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fastapi-app
Bootstrap a new FastAPI backend the way this owner builds them: async SQLAlchemy 2.0 with asyncpg, Alembic migrations, Pydantic v2 settings, a layered structure (routers, services, models, schemas), JWT auth, and the house git and CI workflow. Deployable to a container or Vercel.
First read the shared rules (they override anything you remember):
../shared/house-rules.md, ../shared/no-ai-attribution.md,
../shared/git-and-ci.md, ../shared/docs-and-context.md,
../shared/hardening.md, and (for public repos) ../shared/open-source-docs.md.
Step 0. Get the brief, then ask the variant questions (hard stop)
This is a hard stop. Do not run any scaffolding command until the user has answered.
First, get the project brief: one paragraph on what the service does, its main resources and endpoints, who calls it, and any hard constraints. If the user has not given one, ask for it. The brief drives naming, the domain modules, and the data model.
Then ask the variant questions. If a choice has multiple options, ask; do not assume. Ask in one batch, then proceed.
- Repo visibility: private, open-source, or private-plus-open-source.
- Auth: JWT (python-jose or PyJWT), OAuth (Google), API-key, or none yet.
- Database: Postgres via async SQLAlchemy + asyncpg (default), or none yet.
- Dependency tooling:
uv(default, fast) orpip+requirements.txt. - Admin UI: SQLAdmin, or none.
- Deploy target: Docker container (default) or Vercel serverless.
If the user already answered some, do not re-ask.
Step 1. Verify environment and current versions
- Check Python (
python3 --version, want a current supported 3.x). - Run
scripts/check-latest.shfor current stable versions from PyPI. Pin those, not versions from memory (../shared/house-rules.mdrule 2). - Pull current FastAPI, SQLAlchemy 2.0, and Pydantic v2 docs via Context7 before
writing code (
../shared/docs-and-context.md). SQLAlchemy 2.0 async and Pydantic v2 both broke v1 patterns; do not write v1-era code from memory.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 88 lines · 103 tokens per session scan A d4ae59e8dace
fastapi-app is a skill published in the GitHub repository ccplugins/awesome-claude-code-plugins (929 stars, last pushed 20d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,071 once invoked, about $0.0005 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 skills, from other repositories
e2e-test-skill
E2E test skill for validation.
dynamic-workflow-patterns
Pattern taxonomy, agent role combinations, model routing, unit-of-work sizing, review-findings settling, and resilience discipline for Claude Code dynamic workflows. ALWAYS load this skill before authoring or running any Workflow tool script, and ALWAYS load it when the user mentions "workflow" or "ultracode" in any…
serena-tool-selection
MANDATORY tool selection protocol for Serena LSP tools vs Claude Code built-in tools. ALWAYS use when your tools list includes any mcpserena tools. This skill OVERRIDES default tool selection behavior for code navigation tasks.
diagram-drawio
Skill "diagram-drawio" from lc-semba-ryuichiro/semba-claude-plugins, covering draw\.io図作成ガイドライン, 目次, 事前準備チェックリスト, 図の設計原則 and 段階的開示（progressive disclosure）.
webpify
Skill "webpify" from lc-semba-ryuichiro/semba-claude-plugins, covering webpify 使用ガイド, 目次, 概要, 事前準備チェックリスト and 実行方法.
atl-fetch-confluence
Skill "atl-fetch-confluence" from lc-semba-ryuichiro/semba-claude-plugins, covering confluence 情報取得ガイド, 目次, 概要, 事前準備チェックリスト and 実行方法.