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/compilet-dev/agent-skill-uselink/uselink-api-docsnpx skills add compilet-dev/agent-skill-uselink --skill uselink-api-docsgit clone --depth 1 https://github.com/compilet-dev/agent-skill-uselinkWrote 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/compilet-dev/agent-skill-uselink/uselink-api-docs)<a href="https://agentmods.dev/skills/compilet-dev/agent-skill-uselink/uselink-api-docs"><img src="https://agentmods.dev/badge/skills/compilet-dev/agent-skill-uselink/uselink-api-docs.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 | $0.00050 | $0.01406 |
| Opus 5 | $0.00025 | $0.00703 |
| Sonnet 5 | $0.00010 | $0.00281 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
uselink-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 4d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Docs → Uselink
Scan a codebase for API endpoints, generate clean API documentation as HTML, and publish to uselink.
When to Use
- "Generate API docs and share them"
- "Document our endpoints for the frontend team"
- "Share the API contract with the mobile dev"
- "What endpoints do we have? Publish a reference."
Prerequisites
which uselink || echo "MISSING"
test -f ~/.uselink/config.json && echo "OK" || echo "NO_CONFIG"
Workflow
1. Detect framework and find endpoints
Micronaut/Kotlin:
grep -rn "@Controller\|@Get\|@Post\|@Put\|@Delete" \
--include="*.kt" -l | grep -v build | grep -v test
Express/Node:
grep -rn "router\.\(get\|post\|put\|delete\)\|app\.\(get\|post\|put\|delete\)" \
--include="*.ts" --include="*.js" -l | grep -v node_modules | grep -v test
FastAPI/Python:
grep -rn "@app\.\(get\|post\|put\|delete\)\|@router\.\(get\|post\|put\|delete\)" \
--include="*.py" -l | grep -v __pycache__ | grep -v test
Spring/Java:
grep -rn "@RestController\|@GetMapping\|@PostMapping\|@RequestMapping" \
--include="*.java" --include="*.kt" -l | grep -v build | grep -v test
2. Read each controller
For each controller file:
- Extract the base path (e.g.,
@Controller("/api/v1/documents")) - Extract each endpoint: method, path, query params, body type, return type
- Extract auth requirements (e.g.,
@Secured, middleware) - Read the request/response DTOs to get field names and types
3. Group endpoints
Group by resource/domain:
/api/v1/documents/*→ Documents/api/v1/auth/*→ Authentication/api/v1/comments/*→ Comments
4. Generate HTML
Write to /tmp/uselink-api-docs-<project>-<timestamp>.html.
<!-- API header -->
<div class="card">
<h3>{{PROJECT}} API Reference</h3>
<p class="muted">{{ENDPOINT_COUNT}} endpoints · Generated {{DATE}}</p>
<p>Base URL: <code>{{BASE_URL}}</code></p>
</div>
<!-- Table of contents -->
<h2>Endpoints</h2>
<table>
<thead><tr><th>Method</th><th>Path</th><th>Description</th><th>Auth</th></tr></thead>
<tbody>
<tr>
<td><span class="tag tag-done">POST</span></td>
<td><code>{{PATH}}</code></td>
<td>{{SHORT_DESC}}</td>
<td>{{AUTH_REQUIREMENT}}</td>
</tr>
</tbody>
</table>
<!-- Per-resource sections -->
<h2>{{RESOURCE_NAME}}</h2>
<!-- Per-endpoint detail -->
<h3><span class="tag tag-done">POST</span> <code>{{PATH}}</code></h3>
<div class="card">
<p>{{DESCRIPTION}}</p>
<h4>Query Parameters</h4>
<table>
<thead><tr><th>Name</th><th>Type</th><th>Required</th><th>Description</th></tr></thead>
<tbody>
<tr><td><code>{{PARAM}}</code></td><td>{{TYPE}}</td><td>{{REQ}}</td><td>{{DESC}}</td></tr>
</tbody>
</table>
<h4>Request Body</h4>
<pre><code>{{REQUEST_JSON_EXAMPLE}}</code></pre>
<h4>Response</h4>
<pre><code>{{RESPONSE_JSON_EXAMPLE}}</code></pre>
</div>
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.
- 4d ago First seen · 147 lines · 50 tokens per session scan A f11013cb4712
uselink-api-docs is a skill published in the GitHub repository compilet-dev/agent-skill-uselink (2 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 1,406 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 2026-08-31.
Other skills, from other repositories
talisman
Generate a polished, on-brand PDF guide/handbook/whitepaper from a codebase or project using LaTeX (.tex -> .pdf) or Markdown->pandoc->pdf, with a designed cover page, the product's real brand colors and logo, a subtle branded page background, and TikZ diagrams (domain models, flows, state machines). Use for any…
report
Render a research, documentation, or analysis report as a designed HTML document using the project template, instead of emitting a raw .md file. Use whenever the user asks for a report, analysis, deep-dive, investigation, postmortem, summary, write-up, briefing, or any structured long-form (>500 words, multiple…
docs-organization
Organize project documentation by size, audience, and freshness. Trigger when setting up docs for a new project, restructuring existing documentation, slimming a bloated CLAUDE.md/AGENTS.md, deciding where a doc should live, or on doc best practices questions. Also trigger when CLAUDE.md exceeds 250 lines or docs are…
readme-demo-recorder
Record a polished, scripted-flow browser demo of an HTML page (or URL) for a README hero. Drives Playwright with a fake cursor + click pulse, then encodes WebM → MP4 + GIF tuned for GitHub asset rendering. Use when the user asks to "record a demo", "make a README gif", "capture a screencast of an HTML app", or ships a…
claude-md-optimizer
Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native…
context7-auto-research
Automatically fetches up-to-date documentation from Context7 when users ask about libraries, frameworks, APIs, or need code examples. Triggers proactively without explicit user request.