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 skills add compilet-dev/agent-skill-uselink --skill uselink-onboardinggit 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-onboarding)<a href="https://agentmods.dev/skills/compilet-dev/agent-skill-uselink/uselink-onboarding"><img src="https://agentmods.dev/badge/skills/compilet-dev/agent-skill-uselink/uselink-onboarding/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.
<a href="https://agentmods.dev/skills/compilet-dev/agent-skill-uselink/uselink-onboarding"><img src="https://agentmods.dev/badge/skills/compilet-dev/agent-skill-uselink/uselink-onboarding.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00058 | $0.01736 |
| Opus 5 | $0.00029 | $0.00868 |
| Sonnet 5 | $0.00012 | $0.00347 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
uselink-onboarding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Guide → Uselink
Scan a codebase, generate a comprehensive getting-started guide for new developers, and publish it to uselink as a shareable link.
When to Use
- "Create an onboarding guide for the new hire"
- "How do I explain this repo to someone new? Publish it."
- "Generate a getting-started doc and share it"
- "Make a dev setup guide I can send to contractors"
Prerequisites
which uselink || echo "MISSING"
test -f ~/.uselink/config.json && echo "OK" || echo "NO_CONFIG"
Workflow
1. Scan the codebase
# Project identity
git remote get-url origin 2>/dev/null
basename "$(git rev-parse --show-toplevel)"
# Build system
for f in Makefile package.json build.gradle.kts Cargo.toml go.mod pyproject.toml docker-compose.yml; do
test -f "$f" && echo "BUILD: $f"
done
# Environment files
ls .env.example .env.sample .env.template 2>/dev/null
ls .tool-versions .node-version .java-version .python-version .ruby-version 2>/dev/null
# Documentation
ls README.md CLAUDE.md CONTRIBUTING.md docs/ .github/CONTRIBUTING.md 2>/dev/null
# Infrastructure
ls Dockerfile docker-compose.yml 2>/dev/null
ls .github/workflows/*.yml 2>/dev/null
# Directory structure
find . -maxdepth 2 -type d -not -path "*/.git*" -not -path "*/node_modules*" -not -path "*/build*" -not -path "*/__pycache__*" | sort
2. Read key files
Read (first 150 lines of each):
README.md— existing setup instructionsCLAUDE.md— architecture and conventionsMakefileor equivalent — available commands.env.example— required environment variablesdocker-compose.yml— required services- Main entry point file
3. Generate HTML
Write to /tmp/uselink-onboarding-<project>-<timestamp>.html.
Sections:
<!-- Welcome -->
<div class="card">
<h3>Welcome to {{PROJECT}}</h3>
<p>{{ONE_LINE_DESCRIPTION}}</p>
<p class="muted">This guide will get you from zero to running the app locally.</p>
</div>
<!-- Prerequisites -->
<h2>Prerequisites</h2>
<div class="card">
<table>
<thead><tr><th>Tool</th><th>Version</th><th>Install</th></tr></thead>
<tbody>
<tr><td>{{TOOL}}</td><td>{{VERSION}}</td><td><code>{{INSTALL_CMD}}</code></td></tr>
</tbody>
</table>
</div>
<!-- Clone & Setup -->
<h2>Clone & Setup</h2>
<div class="card">
<pre><code>git clone {{REPO_URL}}
cd {{PROJECT}}
{{SETUP_COMMANDS}}</code></pre>
</div>
<!-- Environment Variables -->
<h2>Environment Variables</h2>
<div class="card">
<p>Copy the example env file:</p>
<pre><code>cp .env.example .env</code></pre>
<table>
<thead><tr><th>Variable</th><th>Required</th><th>Description</th></tr></thead>
<tbody>
<tr><td><code>{{VAR}}</code></td><td>{{REQ}}</td><td>{{DESC}}</td></tr>
</tbody>
</table>
</div>
<!-- Running Locally -->
<h2>Running Locally</h2>
<div class="card">
<pre><code>{{RUN_COMMANDS}}</code></pre>
<p class="muted">The app should be available at <code>{{LOCAL_URL}}</code></p>
</div>
<!-- Architecture Overview -->
<h2>Architecture</h2>
<div class="card"><pre><code>{{ASCII_DIAGRAM}}</code></pre></div>
<p>{{ARCHITECTURE_DESCRIPTION}}</p>
<!-- Directory Guide -->
<h2>Where Things Live</h2>
<table>
<thead><tr><th>Path</th><th>What's in it</th></tr></thead>
<tbody>
<tr><td><code>{{DIR}}</code></td><td>{{PURPOSE}}</td></tr>
</tbody>
</table>
<!-- Common Commands -->
<h2>Common Commands</h2>
<table>
<thead><tr><th>Command</th><th>What it does</th></tr></thead>
<tbody>
<tr><td><code>{{CMD}}</code></td><td>{{DESC}}</td></tr>
</tbody>
</table>
<!-- Conventions -->
<h2>Conventions</h2>
<div class="card">
<ul>
<li><strong>{{CONVENTION}}</strong> — {{EXPLANATION}}</li>
</ul>
</div>
<!-- First Task Suggestions -->
<h2>Good First Tasks</h2>
<div class="card">
<ol>
<li>{{TASK}} — {{WHY_ITS_GOOD_FOR_NEW_DEVS}}</li>
</ol>
</div>
<!-- Who to Ask -->
<h2>Who to Ask</h2>
<div class="card">
<table>
<thead><tr><th>Area</th><th>Person</th></tr></thead>
<tbody>
<tr><td>{{AREA}}</td><td>{{PERSON_OR_PLACEHOLDER}}</td></tr>
</tbody>
</table>
<p class="muted">Not sure? Check <code>git blame</code> on the file you're working in.</p>
</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.
- 9d ago First seen · 193 lines · 58 tokens per session scan A 181cc2c423cc
uselink-onboarding is a skill published in the GitHub repository compilet-dev/agent-skill-uselink (2 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 1,736 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
handoff
Use when a feature or code change made by Claude is complete and the developer wants to confirm they actually understood it before shipping. Triggers on "handoff", "quiz me", "comprehension check", "did I understand this", "verify I read the code", "test my understanding", or after finishing a feature when the…
eli5
Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific person or audience…
wong
Compile everything Claude did today across ALL sessions and repos into one dated teaching-guide markdown saved in "/Daily Log", render it as a phone-readable PDF, and upload to Google Drive. Safe to run multiple times a day — it appends only newly-uncovered work to that day's single file rather than overwriting. Use…
youtube-course-builder
Use when the user wants to learn something, asks for a video, or says "teach me X", "I want to learn X", "how does X work", "explain X", "is there a video about X", "recommend a course/tutorial on X". Builds a progressive YouTube course through wide, creative search, reading the transcript and the comments before…
oral-english-practice
A Claude Code skill that stores and analyses spoken-English practice completed in the Claude app. The app handles the conversation; this skill keeps reports, scores, mistakes, progress trends, and the next practice focus.
game-programming-languages
Game programming languages - C#, C++, GDScript. Learn syntax, patterns, and engine-specific idioms for professional game development.