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 girijashankarj/cursor-handbook --skill websearchgit clone --depth 1 https://github.com/girijashankarj/cursor-handbookWrote 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/girijashankarj/cursor-handbook/websearch)<a href="https://agentmods.dev/skills/girijashankarj/cursor-handbook/websearch"><img src="https://agentmods.dev/badge/skills/girijashankarj/cursor-handbook/websearch/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/girijashankarj/cursor-handbook/websearch"><img src="https://agentmods.dev/badge/skills/girijashankarj/cursor-handbook/websearch.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 | $0.00032 | $0.00387 |
| Opus 5 | $0.00016 | $0.00193 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
websearch 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 5d 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
Skill: Web search
Trigger
When the user asks about a library version, recent API change, or "latest way to do X" and the answer may have changed.
Steps
- Query — Form a short search query (library name, version, and topic).
- Search — Use the web search tool to fetch 1–2 authoritative results (official docs, release notes).
- Synthesize — Summarize the finding and cite the source; apply to the user’s codebase if relevant.
- Caveat — Note if the result is version-specific or may vary by environment.
Rules
- Prefer official docs and release notes over random blog posts.
- Do not paste long copied text; summarize and link.
Prerequisites
- Web search tool available
- User question is version- or time-sensitive (e.g. "latest", "React 19", "Node 22")
Completion Checklist
- Query used and source cited
- Summary in 2–4 sentences
- Version or date caveat if applicable
If Step Fails
- No results: Broaden query (e.g. "React useEffect" instead of "React 19 useEffect")
- Outdated result: Add "as of [date]" or "check latest docs"
- Conflicting info: Prefer official docs; note disagreement
Example
Query: "Express 5 migration guide". Result: Express 5 release notes, breaking changes. Summary: async handlers, req.query changes. Caveat: Express 5.x as of 2025.
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.
- 5d ago First seen · 38 lines · 32 tokens per session scan A 37839a78c0cf
websearch is a skill published in the GitHub repository girijashankarj/cursor-handbook (30 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 387 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 2026-09-03.
Other skills, from other repositories
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
mobile-rn-screen
Polish an existing React Native screen to feel intentional, native, and human-crafted. Use for "this screen looks off", "feels clunky on iOS", "Android version looks wrong", "jank when scrolling", "button is unreachable", or any RN-specific UX polish pass.
mobile-emulator-test
QA a native Android build end-to-end on the emulator. Use for "test on emulator", "QA Android build", "verify native build", "white screen", "cache rehydration", "Expo dev-client QA", "adb reverse". Pairs Metro/adb walk with Supabase + Sentry MCPs for three-layer CRUD verification.
design-generative-art
Create original algorithmic visuals with p5.js, Canvas, or SVG using seeded randomness and interactive controls. Use when "generative art", "procedural visuals", "flow fields", "particle system", or "art from code". Data charts → data-visualization. UI illustration → design-frontend.
audit-security
Static OWASP review of app code (injection, headers, deps). Use when "review security" or "check vulnerabilities". Session/route×gate/getSession → audit-auth-flows. Plan-only burndown → plan-security-audit. Table RLS → plan-rls-audit. LLM attacks → audit-llm-security.