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/vericle/heyclaw/web-searchnpx skills add vericle/heyclaw --skill web-searchgit clone --depth 1 https://github.com/vericle/heyclawWrote 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/vericle/heyclaw/web-search)<a href="https://agentmods.dev/skills/vericle/heyclaw/web-search"><img src="https://agentmods.dev/badge/skills/vericle/heyclaw/web-search.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00460 |
| Opus 5 | $0.00008 | $0.00230 |
| Sonnet 5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
web-search 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
Web search
Use this skill when the user explicitly asks to search for, verify, or check information on the Internet, or when the answer necessarily requires up-to-date information.
Procedure
- Call
mcp_perplexity_perplexity_search. HeyClaw's LLM will synthesize the returned sources, so do not useperplexity_askfor the normal search path. - Write a specific, self-contained
query. Include only the conversational context needed to understand the request and include the current date when the user asks for today's or other time-sensitive information. - Retrieve only what the request needs. For a single fact or short spoken answer,
start with
max_results: 3andmax_tokens_per_page: 256. Use 4-5 results or 512 tokens per page only when the user asks for a comparison, multiple-source verification, or more detail. Do not increase both mechanically. - Set
search_recency_filteronly when freshness is part of the request or the information is likely to have changed. Matchhour,day,week,month, oryearto the actual time window instead of applying a news-specific default. - Base the answer on the returned snippets. Cross-check claims across the results when possible, and preserve facts, names, numbers, and dates accurately.
- If the results are insufficient and
mcp_perplexity_perplexity_askis available, use it once as a fallback withsearch_context_sizeset tolowand the matching recency filter. Do not call both tools routinely. - If the search returns no useful information or fails, say so briefly without inventing anything.
Spoken response
Summarize the result naturally and concisely in the user's language. Do not speak URLs, Markdown, citation numbers, server or tool names, and do not describe the internal process.
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 · 36 lines · 15 tokens per session scan A 4ed674a1ab99
web-search is a skill published in the GitHub repository vericle/heyclaw (17 stars, last pushed 26d ago), licensed MIT. It adds 15 tokens to every session and 460 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 2026-08-30.
Other skills, from other repositories
documentation-server
Use when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval. Also use when interacting with the documentation server web interface, managing uploads, or performing AI-powered document analysis. Use this instead of MCP-native…
ai-film-studio
AI film production studio with pre-built scripts: analyze inspiration/reference videos (Gemini), write script + storyboard, generate stills (GPT Image 2; Seedream 5 / Nano Banana as fallbacks), video (Gemini Omni 1.1 Flash, Seedance 2.5/2.0, LTX 2.5/2.3; Veo 3.1 fallback), audio (ElevenLabs), and assemble the final…
short-video
Short Video Agent Kit. Prefer MCP tools if connected; otherwise the package CLI.
kirok
The ultimate, autonomous memory skill for the Kirok MCP server. Teaches the AI to proactively manage long-term memory (Retain, Recall, Reflect) without explicit user prompting. Establishes strict bank taxonomy and operational rules.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
model-update
新增或更新 CCX 项目中的模型注册技能。适用于 Claude 与非 Claude 模型，覆盖能力表、路由白名单、基准映射、代码生成与验证。.