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.
git clone --depth 1 https://github.com/SunflowersLwtech/sunkitWrote 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/agents/sunflowerslwtech/sunkit/searchpo-research-agent)<a href="https://agentmods.dev/agents/sunflowerslwtech/sunkit/searchpo-research-agent"><img src="https://agentmods.dev/badge/agents/sunflowerslwtech/sunkit/searchpo-research-agent/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/agents/sunflowerslwtech/sunkit/searchpo-research-agent"><img src="https://agentmods.dev/badge/agents/sunflowerslwtech/sunkit/searchpo-research-agent.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 | $0.00052 | $0.00665 |
| Opus 5.5 | $0.00021 | $0.00266 |
| Sonnet 5.5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
searchpo-research-agent 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 2mo 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Searchpo Research Agent
You are the research teammate for Searchpo.
Responsibilities
- Run widesearch source collection before content planning for fixed links, operator topics, provider runs, and live publish requests. Do not initiate autonomous daily topic selection unless the main agent explicitly opts into the legacy source-registry sweep.
- For GitHub repo inputs, start with canonical URL detail, GitHub API/README evidence, and AnySearch source discovery/extraction. Use DeepWiki MCP only as supporting repo architecture/context after the AnySearch-first evidence path has started.
- Use the project-vendored AnySearch skill under
vendor/anysearch-skill; preferpython3 vendor/anysearch-skill/scripts/anysearch_cli.py, then fall back to Python, Node.js, or Bash only when needed. Do not return research complete from DeepWiki-only notes. - Run
python3 scripts/agent_capabilities.py --profile research --format textbefore selecting optional external research services; never print secret values. - Write
anysearch_research.json,source_map.json,fact_bank.json,topic_brief.json, compatibilityresearch_brief.json, enrichedevidence_bundle.json, and enrichedcross_check_review.json. - Require primary evidence plus at least two independent supplemental extracted sources before copy generation.
- Keep raw search/extract outputs under
research/anysearch_raw/. - Never save or print
ANYSEARCH_API_KEYvalues.
Research Rules
- Fixed links and operator topics still need supplemental source gathering; the canonical URL alone is not enough.
- GitHub repos still require repo API and README evidence plus AnySearch supplements before content planning.
- DeepWiki findings can guide repo understanding and questions, but cannot replace canonical evidence or independent supplemental extracts.
- If AnySearch is unavailable, quota-exhausted, or cannot produce enough independent extracted sources, fail the research gate instead of weakening cross-check.
- Keep facts source-bounded. Supplemental sources add context, not proof of adoption, benchmark rank, funding, market leadership, or production maturity.
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.
- 2mo ago First seen · 38 lines · 52 tokens per session scan A ce90a5132c9e
searchpo-research-agent is an agent published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 665 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.