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/plugins/sunflowerslwtech/sunkit/searchpo)<a href="https://agentmods.dev/plugins/sunflowerslwtech/sunkit/searchpo"><img src="https://agentmods.dev/badge/plugins/sunflowerslwtech/sunkit/searchpo/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/plugins/sunflowerslwtech/sunkit/searchpo"><img src="https://agentmods.dev/badge/plugins/sunflowerslwtech/sunkit/searchpo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
searchpo 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.
What it actually says
{
"name": "searchpo",
"version": "1.0.0",
"description": "OSS Radar search pipeline: data prep, agent harness, research/impl agents, and the searchpo-full-flow command.",
"author": {
"name": "SunflowersLwtech"
},
"repository": "https://github.com/SunflowersLwtech/sunkit",
"keywords": ["search", "oss-radar", "pipeline", "agents"],
"skills": "./skills/",
"commands": [
"./commands/searchpo-full-flow.md"
]
}
What it installs
The manifest is a name and a version. 8 skills, 1 command, 3 agents, 1 plugin travel with it, and installing the plugin installs all of them — 582 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill remotion-best-practices A 42 tokens
- Skill searchpo-main-agent A 44 tokens
- Skill searchpo-impl-agent A 31 tokens
- Skill searchpo-full-flow A 74 tokens
- Skill searchpo-research-agent A 43 tokens
- Skill searchpo-agent-capabilities A 48 tokens
- Skill searchpo-plugin-check A 83 tokens
- Skill searchpo-deepwiki-research A 47 tokens
- Command searchpo-full-flow A 22 tokens
- Agent searchpo-main-agent A 54 tokens
- Agent searchpo-impl-agent A 42 tokens
- Agent searchpo-research-agent A 52 tokens
- Plugin github-repo-to-x-threads 2 inside A not measured
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 · 15 lines scan A 7216bd471a8b
searchpo is a plugin published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
antimicrobial-resistance-scientist
Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim…
catalysis-scientist
Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator…
behavioral-ecologist
Reasons from versioned ethograms, Altmann focal/scan sampling, and activity budgets; scores with BORIS (Cohen’s κ), analyzes sequences with Markov/HMM tools, runs sham-controlled playbacks under ARRIVE 2.0, and fits GLMMs on the correct experimental unit while treating pseudoreplication, spatial autocorrelation, and…
hermes-blind
Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts.
sharp-edges
Identify error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes.
ui-input-skills
Form systems, search, and filter components for user input and data collection.