claude-code-sample

claude-code-sample is a skill for Claude Code, Codex from andersonamaral2/Claude-Code-to-Deep-Agents-Skills-Converter. It costs 0 tokens per session (550 once invoked), scanned B, original, MIT.

A recipe for creating a simple Todo web API with FastAPI, SQLite, and basic create, read, update, and delete operations. FastAPI is a Python framework for building web APIs, and SQLite is a small file-based database.

In plain words
What is it for?
Use it when you need a Python 3.11+ todo app, task manager API, or basic REST API backed by SQLite.
Why use it?
It gives a ready sequence for building a small REST API instead of starting from an empty project. It is intended for todo apps, task managers, and similarly simple services.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it when you need a Python 3.11+ todo app, task manager API, or basic REST API backed by SQLite.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andersonamaral2/claude-code-to-deep-agents-skills-converter/claude-code-sample
Install

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.

Any agent
npx skills add andersonamaral2/Claude-Code-to-Deep-Agents-Skills-Converter --skill claude-code-sample
Clone the repo
git clone --depth 1 https://github.com/andersonamaral2/Claude-Code-to-Deep-Agents-Skills-Converter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for claude-code-sample

README.md
[![agentmods](https://agentmods.dev/badge/skills/andersonamaral2/claude-code-to-deep-agents-skills-converter/claude-code-sample/github.svg)](https://agentmods.dev/skills/andersonamaral2/claude-code-to-deep-agents-skills-converter/claude-code-sample)
Your own site
<a href="https://agentmods.dev/skills/andersonamaral2/claude-code-to-deep-agents-skills-converter/claude-code-sample"><img src="https://agentmods.dev/badge/skills/andersonamaral2/claude-code-to-deep-agents-skills-converter/claude-code-sample/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.

agentmods 80×15 button for claude-code-sample

Your own site · 80×15
<a href="https://agentmods.dev/skills/andersonamaral2/claude-code-to-deep-agents-skills-converter/claude-code-sample"><img src="https://agentmods.dev/badge/skills/andersonamaral2/claude-code-to-deep-agents-skills-converter/claude-code-sample.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 550 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 61
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Data Exfiltration · line 70
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00550
Opus 5 $0.00000 $0.00275
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 10d ago against content hash e90f0b71d26e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

claude-code-sample scanned grade B with 2 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 10d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST http://localhost:8000/todos -H "Content-Type: application/json" -d '{"title": "Buy milk", "completed": false}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8000/todos
examples/claude-code-sample/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Python FastAPI Todo App

Creates a simple Todo API with FastAPI, SQLite, and basic CRUD operations.


When to use

When the user asks to create a todo app, task manager API, or simple REST API with Python.


Steps

First, make sure Python 3.11+ is installed. On macOS use brew install [email protected], on Linux use apt-get install python3.11.

Create the project directory and initialize a virtual environment:

mkdir -p todo-api/app
cd todo-api
python3 -m venv venv
source venv/bin/activate

Install the dependencies: pip install fastapi uvicorn sqlalchemy

Create the file app/database.py:

from sqlalchemy import create_engine
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker

DATABASE_URL = "sqlite:///./todos.db"

engine = create_engine(DATABASE_URL, connect_args={"check_same_thread": False})
SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
Base = declarative_base()

Create the file app/models.py:

from sqlalchemy import Column, Integer, String, Boolean
from .database import Base

class Todo(Base):
    __tablename__ = "todos"

    id = Column(Integer, primary_key=True, index=True)
    title = Column(String, index=True)
    description = Column(String, default="")
    completed = Column(Boolean, default=False)

Create app/main.py with the FastAPI app, including these endpoints:

  • GET /todos — list all todos
  • POST /todos — create a new todo
  • PUT /todos/{id} — update a todo
  • DELETE /todos/{id} — delete a todo

The app should read $API_HOST and $API_PORT from the environment for the server bind address.

Add the project conventions to CLAUDE.md at the root.

Test the API:

curl http://localhost:8000/todos
curl -X POST http://localhost:8000/todos -H "Content-Type: application/json" -d '{"title": "Buy milk", "completed": false}'

For each endpoint, run a quick smoke test to make sure it returns 200.

Read the full file on GitHub · 86 lines

Changes

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.

  1. 10d ago First seen · 86 lines · 0 tokens per session scan B e90f0b71d26e

Subscribe to this mod's changes

claude-code-sample is a skill published in the GitHub repository andersonamaral2/Claude-Code-to-Deep-Agents-Skills-Converter (57 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 550 tokens. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.