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-reportgit 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-report)<a href="https://agentmods.dev/skills/compilet-dev/agent-skill-uselink/uselink-report"><img src="https://agentmods.dev/badge/skills/compilet-dev/agent-skill-uselink/uselink-report/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-report"><img src="https://agentmods.dev/badge/skills/compilet-dev/agent-skill-uselink/uselink-report.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 | $0.00923 |
| Opus 5 | $0.00024 | $0.00462 |
| Sonnet 5 | $0.00010 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
uselink-report 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Uselink Report Generator
See
report-templates.mdfor HTML templates and per-report-type data gathering commands.
Prerequisites
Before generating any report, verify:
- CLI installed --
which uselinkmust resolve. If not, tell the user to runnpm install -g uselink. - CLI configured --
~/.uselink/config.jsonmust exist withapi_key. If not, tell the user to runuselink loginin their terminal (interactive -- Claude cannot run it).
Stop here if either check fails. The user must fix these.
Report Types
| Type | Trigger phrases | Data sources |
|---|---|---|
| Code review | "review report", "code review summary" | git diff, file reads, grep |
| Architecture | "architecture report", "system overview" | Directory scan, key config files |
| Sprint/daily | "sprint report", "daily summary", "standup" | git log --since, gh pr list |
| Custom | Anything else that asks for a "report" | Conversation context, user instructions |
If the type is ambiguous, ask. Do not guess.
Workflow
- Determine report type from the user's request.
- Gather data using the commands and file reads listed in
report-templates.mdfor that report type. - Generate HTML by filling the matching template from
report-templates.md. Write to/tmp/uselink-report-<type>-<timestamp>.html. - Publish with
uselink publish <file> --title "<Report Title>" --format html. - Return the URL as the primary output.
Key Rules
- Always use
--format html. Reports are HTML, not markdown. - Title format:
<Type> Report -- <Project> -- <Date>. Example:Code Review -- my-project -- 2026-05-25. - Infer project name from the git remote or directory name.
- Date in titles uses
YYYY-MM-DD. - Do not ask the user which template to use -- pick based on the report type.
- The temp file is not cleaned up so the user can re-publish after edits.
Content Rules
- Use real data from the repo. Never fabricate commits, file names, or findings.
- For code review reports, run the actual diff and analyze it. Do not summarize from memory.
- For sprint reports, use
git logoutput, not guesses about what was worked on. - Keep reports concise. A 200-line HTML report is better than a 2000-line one.
What ships with it
1 file 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.
- 9d ago First seen · 69 lines · 49 tokens per session scan A b1d3b75f4be4
uselink-report 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 923 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
sync
Synchronize task files and source-of-truth documents. Update NEXT-TASKS.md, FUTURE-ENHANCEMENTS.md, README, and CHANGELOG to reflect current project state.
story
Track tickets, issues, and progress for your project. Load project context, manage sessions, guide setup.
story
Track tickets, issues, and progress for your project. Load project context, manage sessions, guide setup.
wrap
Session wrap-up: consolidates every descriptive markdown file (README.md, AGENTS.md, HANDOFF.md, docs/) into ONE canonical CLAUDE.md, then reconciles it against the current code state so a fresh session or new teammate can pick up immediately. CLAUDE.md keeps a mandatory PROGRESS block at the top answering two…
yolo-status
Use when the user asks where things stand, what's in progress, or "where was I". Computes a derived view of every feature's status from git and the briefs — nothing is read from a stored status field.
yolo-roadmap
Use when the user has a large or fuzzy goal that should be decomposed into several features. Produces N feature briefs (optionally sharing a milestone label) — a one-time act that returns briefs, not a container. Triggers on "break this epic into features", "plan a milestone", "decompose this".