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/joinwell52-ai/codeflowmu-open/web-searchnpx skills add joinwell52-AI/CodeFlowMu-open --skill web-searchgit clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-openWrote 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/joinwell52-ai/codeflowmu-open/web-search)<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/web-search"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/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 | $0.00045 | $0.00492 |
| Opus 5 | $0.00023 | $0.00246 |
| Sonnet 5 | $0.00009 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Search
Find the smallest credible source set that can answer the research question. This skill discovers and selects sources; it does not extract full page content or write the final research report.
Workflow
- Convert the request into one or more answerable research questions.
- Identify unstable facts that require current web verification.
- Construct focused queries using the subject, required fact, date or version, geography, and preferred source type.
- Search broadly enough to discover alternatives, then narrow quickly.
- Prefer sources in this order when applicable:
- Official documentation, standards, laws, datasets, or first-party announcements.
- Primary research papers or original technical sources.
- Reputable organizations with direct evidence.
- High-quality secondary analysis for context or disagreement.
- Check title, publisher, publication date, event date, snippet relevance, and URL before selecting a source.
- Remove duplicates, mirrors, SEO pages, and sources that merely repeat another source.
- Hand selected URLs and the reason for selection to
web-extractorweb-research.
Query Rules
- Use one intent per query where possible.
- Add official domains or source-type terms when authority matters.
- Add exact product versions, model names, dates, or error strings when precision matters.
- For contested questions, search for both supporting and contradicting evidence.
- Stop expanding queries once the selected sources are sufficient and authoritative.
Output Contract
For every selected result, preserve:
{
"query": "the query used",
"title": "result title",
"source_url": "https://example.com/page",
"publisher": "source owner",
"published_at": "known date or null",
"source_type": "official|primary|secondary",
"selection_reason": "why this source is useful"
}
Guardrails
- Do not treat search snippets as evidence for the final conclusion.
- Do not invent publication dates, publishers, or URLs.
- Do not select many weak sources when one authoritative source is available.
- Do not use
browser-playwright-checkas a substitute for source discovery.
What ships with it
1 file 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.
- 5d ago First seen · 55 lines · 45 tokens per session scan A ca207e81d547
web-search is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 11d ago), licensed MIT. It adds 45 tokens to every session and 492 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 2026-08-31.
Other skills, from other repositories
agentbro-release
Use when releasing AgentBro from this repository: merging dev/main, bumping versions, updating release notes, tagging, pushing, monitoring GitHub Actions, Homebrew cask publication, or fixing a bad release.
agentbro-pr-merge
Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.
source-command-check
跑全套本地校验(前端 lint/test/build + Rust check)。.
oculpm-journal
MCP 도구가 보이면 이 스킬 대신 도구를 쓴다 — journalwrite / planstatus / planupdate 가 경로·파일명·frontmatter 규격을 서버에서 보장한다. 아래는 도구가 없을 때 파일을 직접 쓰는 규격이다.
self-audit
작업을 "완료"라고 보고하기 직전, 스스로 결과를 감사할 때. 커밋/PR 직전 최종 점검에도 사용.
project-inception
Use when kicking off a new project or feature area in an ocul-pm tracked project (.oculpm/ present) — research the stack landscape via web search, then converse with the user (research-backed choices) to settle the optimal spec, and seed a discussion doc, a detailed 3-depth plan (plancreate), EVALS.md done-criteria…