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/rubenzarroca/sdd-plugin/sdd-api-docsnpx skills add rubenzarroca/sdd-plugin --skill sdd-api-docsgit clone --depth 1 https://github.com/rubenzarroca/sdd-pluginWhat 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 | $0.00071 | $0.01632 |
| Opus 5 | $0.00036 | $0.00816 |
| Sonnet 5 | $0.00014 | $0.00326 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
sdd-api-docs 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 3d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd:api-docs — Fetch and cache external API documentation
You are fetching real documentation for an external API/service and caching it locally so that all downstream SDD commands (plan, implement) use verified API contracts instead of assumptions from training data.
Why this exists: Claude's training data may contain outdated, incomplete, or incorrect API documentation. When building integrations, this causes code that looks correct but fails at deploy time. This skill forces a documentation-first approach: read the real docs, cache them locally, and use them as the single source of truth.
Step 1: Parse arguments
Parse from $ARGUMENTS:
- Service name (required): kebab-case identifier (e.g.,
stripe,bigquery,holded-api) - Docs URL (optional): direct URL to the API documentation
If no service name is provided, ask: "Which external service do you need to document? Give me the name and optionally the URL to its API docs."
Step 2: Check for existing cache
Check if .sdd/api-docs/{service-name}.json already exists by calling sdd_api_list with the service name.
If it exists, report:
- When it was fetched (
fetched_at) - How many endpoints are cached
- Ask: "Documentation for
{service}is already cached (fetched {date}). Do you want to refresh it or keep the current version?"
If the user wants to keep it, stop.
Step 3: Locate documentation
If a docs URL was provided:
Use WebFetch to read the documentation page. If the page is large or paginated, fetch the most relevant sections:
- Authentication / Authorization
- API reference / Endpoints
- Rate limits
- Error codes
- SDKs / Libraries
If no URL was provided:
Use WebSearch to find the official API documentation:
- Search:
"{service-name}" API documentation site:docs OR site:developer - Identify the official documentation site (prefer official docs over third-party tutorials)
- Use
WebFetchon the official docs pages
Multi-page documentation:
Most API docs span multiple pages. Follow this strategy:
- Fetch the main API reference/overview page first
- Identify the endpoints relevant to the project (cross-reference with the feature spec if one exists in
.sdd/state.json) - Fetch individual endpoint documentation pages as needed
- Stop when you have enough detail for the endpoints the project will actually use — do NOT try to document the entire API
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.
- 3d ago First seen · 159 lines · 71 tokens per session scan A c999bbc999b1
sdd-api-docs is a skill published in the GitHub repository rubenzarroca/sdd-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 71 tokens to every session and 1,632 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
release
Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.
fix
Use to drive a bug fix from first report through close, with a "why didn't we catch it?" loop at the end. Triggers — "/engineer.fix", "a bug came in", "this is broken", "a user reported X", "there's a defect", "we have a regression", "this needs a fix", "another report", "more issues", "still failing", "validation…
neurolink-guide
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.
post-merge
Use immediately after a PR is merged to clean up the local feature branch and resync main. Triggers — "/engineer.post-merge", "did we merge", "did we push", "PR merged", "post-merge cleanup", or right after a gh pr merge succeeds in the same session.
session-retrospective
Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…
vc-predict
5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.