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/zebbern/claude-code-guide/route-to-openapinpx skills add zebbern/claude-code-guide --skill route-to-openapigit clone --depth 1 https://github.com/zebbern/claude-code-guideWrote 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/skills/zebbern/claude-code-guide/route-to-openapi)<a href="https://agentmods.dev/skills/zebbern/claude-code-guide/route-to-openapi"><img src="https://agentmods.dev/badge/skills/zebbern/claude-code-guide/route-to-openapi.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 | $0.00067 | $0.01145 |
| Opus 5 | $0.00034 | $0.00573 |
| Sonnet 5 | $0.00013 | $0.00229 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
route-to-openapi 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 yesterday.
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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
route-to-openapi
Automatically scan route/endpoint definitions in source code and generate RESTful API documentation conforming to the OpenAPI 3.0.3 specification.
Supports major web frameworks with automatic framework detection. Extracts HTTP methods, paths, parameters, request bodies, response models, and doc comments, then outputs a standard OpenAPI spec file ready to import into Swagger UI or Redoc.
Quick Start
# Scan source directory, output OpenAPI spec in JSON format
python scripts/generate_api_doc.py ./src
# Specify output format and file
python scripts/generate_api_doc.py ./src --format yaml --output api-spec.yaml
# Specify framework and API metadata
python scripts/generate_api_doc.py ./app --framework flask --title "My API" --version 2.0.0
# Add server URLs
python scripts/generate_api_doc.py ./routes --server http://localhost:3000 --server https://api.example.com
Supported Frameworks
| Language | Framework | Parsing Method |
|---|---|---|
| Python | Flask | AST parsing (decorators + type annotations + docstrings) |
| Python | FastAPI | AST parsing (decorators + Pydantic models + type annotations) |
| Python | Django REST Framework | AST parsing (@api_view decorators) |
| JavaScript/TypeScript | Express.js | Regex matching (app.get() / router.get() + JSDoc) |
| Go | Gin | Regex matching (r.GET() / group.GET() + comments) |
| Go | Echo | Regex matching (e.GET() + comments) |
Extraction Capabilities
The script automatically extracts the following information:
- HTTP Methods: GET / POST / PUT / DELETE / PATCH, etc.
- Route Paths: Automatically converts each framework's path parameter format to the OpenAPI
{param}format - Path Parameters: Extracted from route patterns (with type inference)
- Query Parameters: Extracted from function signatures (Python frameworks)
- Request Bodies: Inferred from type annotations and Pydantic models (FastAPI)
- Response Models: Extracted from the
response_modelparameter (FastAPI) - Endpoint Descriptions: Extracted from docstrings / JSDoc / inline comments
- Tag Grouping: Automatically grouped by source file module name
What ships with it
2 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.
- yesterday First seen · 130 lines · 67 tokens per session scan A bd4da9fb386e
route-to-openapi is a skill published in the GitHub repository zebbern/claude-code-guide (4,600 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,145 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
business-investment-advisor
../../../finance/business-investment-advisor/skills/business-investment-advisor/SKILL.md.
a11y-audit
../../../engineering-team/a11y-audit/skills/a11y-audit/SKILL.md.
adversarial-reviewer
../../../engineering-team/skills/adversarial-reviewer/SKILL.md.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
app-store-optimization
../../../marketing-skill/skills/app-store-optimization/SKILL.md.