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 icosaedro-git/toolsnap-mcp --skill toolsnapgit clone --depth 1 https://github.com/icosaedro-git/toolsnap-mcpWrote 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/icosaedro-git/toolsnap-mcp/toolsnap)<a href="https://agentmods.dev/skills/icosaedro-git/toolsnap-mcp/toolsnap"><img src="https://agentmods.dev/badge/skills/icosaedro-git/toolsnap-mcp/toolsnap/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/icosaedro-git/toolsnap-mcp/toolsnap"><img src="https://agentmods.dev/badge/skills/icosaedro-git/toolsnap-mcp/toolsnap.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 | $0.00013 | $0.01039 |
| Opus 5.5 | $0.00005 | $0.00416 |
| Sonnet 5.5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
toolsnap 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ToolSnap Skill
Extract exact, reproducible data from web pages and documents through the ToolSnap MCP server, which parses server-side and returns only the answer — large pages never enter the context window. It does not search the web and does not drive a browser; discovery and interaction stay with native tools.
When to Use
- Quoting or citing a page exactly, where an LLM summary could drift
- Turning HTML tables, CSV/JSON files, PDFs, RSS feeds, or sitemaps into structured data
- Querying a large dataset for a few rows instead of loading the whole file
- Auditing SEO metadata (title/canonical/og:*, JSON-LD) as data
- Checking token cost of a document before ingesting it
Keep native web_search for discovery (ToolSnap does not search) and
browser_navigate for JS-heavy SPAs, logins, and page interaction.
Prerequisites
The toolsnap MCP server, installed from the catalog:
hermes mcp install official/toolsnap
It is a remote server on Cloudflare Workers (streamable HTTP) — nothing runs locally and the free tools need no account, API key, or configuration.
How to Run
Call the MCP tools directly. Only a curated core appears in tools/list;
the rest of the catalog is reachable through two meta-tools:
tool_catalog()— families overview;tool_catalog(family="...")ortool_catalog(tool="...")returns a tool's schema.use_tool(name="...", args={...})— execute any cataloged tool, same behavior as a direct call.task_recipes()— ready multi-tool plans (clone a site, SEO audit, …).
Quick Reference
| Task | Tool |
|---|---|
| Quote or cite a page exactly | fetch_extract |
| Rebuild / migrate a page (clean DOM) | fetch_html |
| Tables on a page → JSON/CSV | html_table_extract |
| Query a big CSV/JSON without loading it | csv_query / json_query |
| PDF text | pdf_text_extract |
| Feeds, sitemaps, link audits | rss_parse / sitemap_parse / link_check |
| SEO metadata and JSON-LD | fetch_metadata / fetch_structured |
| Token budget check before ingesting | count_tokens |
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 · 103 lines · 13 tokens per session scan A e611c9419bcb
toolsnap is a skill published in the GitHub repository icosaedro-git/toolsnap-mcp (1 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,039 once invoked, about $0.0001 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
review-stack
Stack review of one or more third-party tools (OXC, TanStack, Vite, cf, Sentry, pnpm, Claude Code...) against current official best practices, or of what a dependency bump brings (bumped): one parallel subagent per tool, verified findings, one consolidated plan in chat. USE WHEN: user runs /review-stack or explicitly…
story-html-publisher
Final step of the AI Storybook pipeline. Consolidates the scenes, images, and per-scene audio into ONE self-contained HTML storybook — a swipe/tap player with every image and audio clip embedded as base64 so the single file works offline and can be shared as-is. Reads {slug}scenes.json, {slug}images.json, and…
polygraph
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to…
cf
USE WHEN: running, finding, or troubleshooting Cloudflare CLI (cf) commands in this repo - dev servers, builds and their Build Output, Env types, startup profiling, production profiles, Workers Issues, and telemetry, local KV/D1/R2 data, the commands that still need Wrangler, or the cf equivalent of a Wrangler habit.…
motion-graphics
Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s…
remotion-to-hyperframes
Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my…