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/rysh-ai/rysh-cli-code/docs-link-checkernpx skills add rysh-ai/rysh-cli-code --skill docs-link-checkergit clone --depth 1 https://github.com/rysh-ai/rysh-cli-codeWhat 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 | $0.00015 | $0.00378 |
| Opus 5 | $0.00008 | $0.00189 |
| Sonnet 5 | $0.00003 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
docs-link-checker 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 2d 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.
What it actually says
You are checking the documentation site at {{start_url}} for broken links, using only the browser (browser_action). Never run shell commands.
Method
- Navigate to {{start_url}}. Use get_elements to collect every link in the site's navigation (sidebar, header, footer) plus in-page links that stay on the same host. External links are out of scope — note them, skip them.
- Visit each collected link once (navigate). Keep a visited list so you
never re-check a URL. For each page record one verdict:
- OK — the page renders with real content.
- BROKEN — an error page (404/500, "page not found") or a navigation failure.
- EMPTY — the page loads but get_text shows no meaningful body (a bare template, a "TODO" stub).
- On each OK page, also collect same-host links you have not seen yet, up to a total of 50 pages checked. Stop at the cap and say the crawl was truncated.
Report
Finish with a summary the reader can act on:
checked N links: X ok, Y broken, Z empty- One line per BROKEN or EMPTY page: the URL, the page that linked to it, and the verdict.
- If everything passed: "all links ok" plus the count.
Verdicts must come from pages you actually visited in this run — never guess a status from the URL shape.
What ships with it
3 files 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.
- 2d ago First seen · 42 lines · 15 tokens per session scan A 55917bf6cef9
docs-link-checker is a skill published in the GitHub repository rysh-ai/rysh-cli-code (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 15 tokens to every session and 378 once invoked, about $0.0001 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
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…
computer-use
Control local desktop applications through Computer Use for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.
canvas
Display, present, and render HTML content on connected Otto nodes (Mac app, iOS, Android). Show on device, preview on mobile, push to screen, or navigate to a URL on any connected node. Use for games, visualizations, dashboards, interactive demos, and live-reloading development previews. Supports presenting, hiding…
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
use-tinyfish
Use TinyFish for web search, fetching URLs, reading pages, current information, source-backed answers, research, docs, pricing/product pages, extraction, scraping, and browser automation. Use whenever the user asks to search, find, look up, research, compare, get information from the web, summarize a URL, fetch page…
agent
Default browser automation agent — click, fill forms, navigate, log in, and extract structured data from any website using a natural-language goal, or run the same task across multiple sites in parallel. New users get 600 free automation credits to start; beyond that it draws on your plan's automation credits (unlike…