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 dajiaohuang/shuiyuan-mcp --skill deepsearchgit clone --depth 1 https://github.com/dajiaohuang/shuiyuan-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/dajiaohuang/shuiyuan-mcp/deepsearch)<a href="https://agentmods.dev/skills/dajiaohuang/shuiyuan-mcp/deepsearch"><img src="https://agentmods.dev/badge/skills/dajiaohuang/shuiyuan-mcp/deepsearch/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/dajiaohuang/shuiyuan-mcp/deepsearch"><img src="https://agentmods.dev/badge/skills/dajiaohuang/shuiyuan-mcp/deepsearch.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 | $0.00065 | $0.00828 |
| Opus 5 | $0.00032 | $0.00414 |
| Sonnet 5 | $0.00013 | $0.00166 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
deepsearch 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepsearch
Use this skill to turn a broad question into a structured investigation. Prefer evidence over speed, but keep the work bounded and visible.
Operating Mode
- Start with a short research frame unless the user asked for silent execution:
- Target question
- Scope boundaries
- 2-5 subquestions
- Likely source classes
- Search in passes. After each pass, update the working hypothesis and the next best query.
- Keep a compact evidence ledger in your notes: claim, source, date, reliability, what it proves, what it does not prove.
- Stop when the answer is supported by enough independent evidence for the stakes, or when further search is unlikely to change the result.
- Present conclusions with confidence and caveats, not a pile of links.
Search Passes
Run at least two passes for nontrivial tasks:
- Pass 1: orientation. Identify names, dates, vocabulary, canonical sources.
- Pass 2: verification. Search exact phrases, official docs, source code, issue trackers, primary records, or archives.
- Optional pass 3: adversarial check. Search for contradictions, failure cases, criticism, or newer updates.
For research that may affect money, health, law, safety, or current decisions, verify against current primary sources.
Tool Routing
- Use web search for public or current facts; browse when information may have changed, primary sources matter, or the user asks for links.
- Use repo/local search (
rg, file reads, tests) for codebase and document investigations. - Use GitHub tools for issues, PRs, releases, and repository metadata when available.
- Use domain MCPs when relevant, such as
mcp__shuiyuan__for Shuiyuan topics and posts. For Shuiyuan-heavy research, readreferences/shuiyuan-mcp.mdto reduce forum requests. - Use browser automation only when page state, login, screenshots, or interactive inspection matters.
Evidence Hygiene
- Do not rely on a single secondary source for important claims.
- Prefer primary sources, then reputable secondary sources, then community reports.
- Prefer exact dates over relative dates.
- Distinguish facts from inference.
- Track source freshness; stale docs and old forum answers may be superseded.
- Avoid over-quoting; summarize instead.
- If a source cannot be opened, say so and do not pretend to have read it.
- When using local files, cite absolute file paths with line numbers when useful.
What ships with it
5 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.
- 12d ago First seen · 87 lines · 65 tokens per session scan A c99a22d40e62
deepsearch is a skill published in the GitHub repository dajiaohuang/shuiyuan-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 828 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…