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-pr-digestgit 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-pr-digest)<a href="https://agentmods.dev/skills/compilet-dev/agent-skill-uselink/uselink-pr-digest"><img src="https://agentmods.dev/badge/skills/compilet-dev/agent-skill-uselink/uselink-pr-digest/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-pr-digest"><img src="https://agentmods.dev/badge/skills/compilet-dev/agent-skill-uselink/uselink-pr-digest.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 | $0.00049 | $0.01373 |
| Opus 5 | $0.00024 | $0.00687 |
| Sonnet 5 | $0.00010 | $0.00275 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
uselink-pr-digest 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Digest → Uselink
Turn a pull request into a clean, readable summary page and publish it to uselink. Stakeholders see what changed and why — without reading diffs.
When to Use
- "Summarize this PR for the PM"
- "Share PR #42 with the team"
- "Create a digest of what this branch does"
- User provides a PR number or URL
Prerequisites
which uselink || echo "MISSING"
test -f ~/.uselink/config.json && echo "OK" || echo "NO_CONFIG"
which gh || echo "GH_MISSING"
If uselink or its config is missing, tell the user to install/configure it. gh CLI is needed for PR metadata.
Workflow
1. Get PR data
From PR number:
gh pr view <number> --json title,body,author,state,additions,deletions,changedFiles,baseRefName,headRefName,mergedAt,createdAt,labels,reviewDecision
gh pr diff <number> --stat
gh pr diff <number> --name-only
From current branch (no PR number given):
gh pr view --json title,body,author,state,additions,deletions,changedFiles,baseRefName,headRefName,mergedAt,createdAt,labels,reviewDecision
git diff origin/main...HEAD --stat
git diff origin/main...HEAD --name-only
From URL:
Extract owner/repo and number from the URL pattern github.com/<owner>/<repo>/pull/<number>.
2. Analyze changes
# Get the full diff for analysis
gh pr diff <number>
# Or for current branch
git diff origin/main...HEAD
Read each changed file and categorize changes:
- New features — new files, new endpoints, new components
- Bug fixes — error handling changes, condition fixes
- Refactoring — renamed files, restructured code, no behavior change
- Config/infra — CI, Docker, dependencies, migrations
3. Generate HTML
Write to /tmp/uselink-pr-digest-<number>-<timestamp>.html.
<!-- PR header -->
<div class="card">
<h3>{{PR_TITLE}}</h3>
<p class="muted">{{AUTHOR}} · {{BASE}} ← {{HEAD}} · {{DATE}}</p>
<div class="summary-grid">
<div class="summary-stat"><div class="num">{{FILES}}</div><div class="label">Files changed</div></div>
<div class="summary-stat"><div class="num" style="color:#22c55e">+{{ADDITIONS}}</div><div class="label">Additions</div></div>
<div class="summary-stat"><div class="num" style="color:#ef4444">-{{DELETIONS}}</div><div class="label">Deletions</div></div>
</div>
</div>
<!-- What changed (plain English) -->
<h2>What Changed</h2>
<div class="card">
<ul>
<li><strong>{{CHANGE_1_TITLE}}</strong> — {{CHANGE_1_DESCRIPTION}}</li>
<!-- One bullet per logical change, not per file -->
</ul>
</div>
<!-- Why (from PR description or commit messages) -->
<h2>Why</h2>
<div class="card"><p>{{MOTIVATION}}</p></div>
<!-- Files changed by category -->
<h2>Files Changed</h2>
<table>
<thead><tr><th>File</th><th>Category</th><th>+/-</th></tr></thead>
<tbody>
<tr><td><code>{{FILE}}</code></td><td><span class="tag tag-done">feature</span></td><td>+{{A}}/-{{D}}</td></tr>
</tbody>
</table>
<!-- Testing notes -->
<h2>How to Test</h2>
<div class="card">
<ol><li>{{TEST_STEP}}</li></ol>
</div>
<!-- Risks / things to watch -->
<h2>Risks</h2>
<div class="card">
<ul><li>{{RISK}}</li></ul>
</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 · 139 lines · 49 tokens per session scan A 3224c0534ff9
uselink-pr-digest is a skill published in the GitHub repository compilet-dev/agent-skill-uselink (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,373 once invoked, about $0.0002 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
Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish. Every step requires user approval.
surface-after-care
Regelmäßiger Pflegedurchlauf für ein bereits veröffentlichtes GitHub-Repository (Stufe 1, günstig und oft wiederholbar): zuerst alle Distributionsflächen des Projekts ermitteln (npm, PyPI, Registries, Marketplaces, Stores, Website) und Änderungen später dorthin spiegeln, dann Topics setzen, Privacy-Gate, Dokumente auf…
pr-summarizer
Generate clear, complete pull request descriptions from a diff or commit list. Use when user needs to write a PR description, wants to document a change, or asks for a commit summary.
yolo-finish
Use when a feature is implemented and verified, to land it. Default path is PR + CI check, with the ship gate confirming before the irreversible merge; fast-local is the escape hatch. Includes the risk classifier whose hard triggers always stop for a human. Triggers on "ship it", "land this", "open a PR", or as the…
git-workflow
Git workflow automation with conventional commits, merge vs rebase decision trees, worktrees, SSH signing, and monorepo sparse checkout patterns.
changelog-generator
Generate CHANGELOG.md from git history grouped by Conventional Commit types. Triggers on "generate changelog", "write changelog", "release notes".