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 hraness/atet --skill save-url-kbgit clone --depth 1 https://github.com/hraness/atetWrote 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/hraness/atet/save-url-kb)<a href="https://agentmods.dev/skills/hraness/atet/save-url-kb"><img src="https://agentmods.dev/badge/skills/hraness/atet/save-url-kb/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/hraness/atet/save-url-kb"><img src="https://agentmods.dev/badge/skills/hraness/atet/save-url-kb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.02133 |
| Opus 5.5 | $0.00044 | $0.00853 |
| Sonnet 5.5 | $0.00022 | $0.00427 |
| Haiku 4.5 | $0.00011 | $0.00213 |
Grade A, and why
save-url-kb scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- save-url-kb — 100% identical, 56 lines differ
- save-url-kb — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture web content
Use the installed kb CLI. Check the available local routes when the capture may need a browser or optional media tools:
kb doctor
kb adapters
Resolve <vault> to the directory containing its authored or managed
index.md front door, then set
the shell-local KB_ROOT to that path (KB_ROOT=kb from a typical repository
root, or KB_ROOT=. from inside the vault). Pass --output "$KB_ROOT/articles"
to captures and read the vault's applicable agent instructions before writing.
Pick the read surface
Start ordinary URL capture with the layered default:
kb clip https://example.com/article --output "$KB_ROOT/articles"
The command tries stable structured data, bounded HTTP extraction, and rendered-browser fallback as needed. If those routes produce no usable source material, URL capture may perform one read-only lookup for an existing Archive.today-family snapshot. It never submits the source for archival. A useful structured provider result, including a partial Hacker News result, remains authoritative over the archive fallback.
When the source is already open in a signed-in browser, read the current tab in place:
kb clip current --browser-live --output "$KB_ROOT/articles"
kb clip current --cdp 9222 --output "$KB_ROOT/articles"
For --browser-live, first enable Chrome's local debugging connection at chrome://inspect/#remote-debugging (Chrome 144+). If Chrome was launched with an explicit loopback debugging port, pass that numeric port to --cdp instead.
Current-tab capture derives the source URL from the attached tab. It does not navigate, click, type, submit, upload, or scroll that tab.
To open a URL with existing browser state, select a profile. A path-backed profile is copied into a temporary snapshot for the capture, so the source profile remains unchanged:
kb clip https://example.com/member/article --browser-profile "$KB_CAPTURE_PROFILE" --output "$KB_ROOT/articles"
Use cookie-backed HTTP when the page does not require browser-only local state, or import a page already saved from any browser:
What ships with it
4 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.
- 1mo ago First seen · 171 lines · 111 tokens per session scan A 496e2d1bb577
save-url-kb is a skill published in the GitHub repository hraness/atet (5 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 2,133 once invoked, about $0.0004 per session on Opus 5.5. 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
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
figures
Makes publication-quality plots from data with matplotlib, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. Use whenever results are plotted, charted or visualized for a paper, report or answer, or…
liteparse
Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally without cloud dependencies.
better-t-stack
Create or extend an end-to-end type-safe TypeScript project with Better-T-Stack (create-better-t-stack). Use when the user wants to start, scaffold or bootstrap an app, API, fullstack project or monorepo with any of Next.js, TanStack Router or Start, React Router, Nuxt, Svelte, Solid, Astro, React Native, Hono…