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/marketplace)<a href="https://agentmods.dev/plugins/sunflowerslwtech/sunkit/marketplace"><img src="https://agentmods.dev/badge/plugins/sunflowerslwtech/sunkit/marketplace/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/marketplace"><img src="https://agentmods.dev/badge/plugins/sunflowerslwtech/sunkit/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sunkit marketplace 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "sunkit",
"owner": {
"name": "SunflowersLwtech",
"url": "https://github.com/SunflowersLwtech"
},
"metadata": {
"description": "SunflowersLwtech's toolbox: Claude Code skills, agents, commands, and MCP servers in one marketplace.",
"version": "1.0.0"
},
"plugins": [
{
"name": "polanyi-design",
"source": "./plugins/polanyi-design",
"description": "Frontend design cognitive engine grounded in Michael Polanyi's tacit knowledge framework. Surfaces expert-level visual judgment in UI design, component architecture, and design systems.",
"category": "design",
"keywords": ["frontend", "design", "ui", "tacit-knowledge"]
},
{
"name": "loopify-requirements",
"source": "./plugins/loopify-requirements",
"description": "Convert prompts, vague tasks, and agent workflows into repeatable, verifiable loops with goal/scope/verification/escalation/stop conditions.",
"category": "workflow",
"keywords": ["loops", "automation", "requirements", "agents"]
},
{
"name": "github-repo-to-x-threads",
"source": "./plugins/searchpo/x-threads",
"description": "Analyze technical sources and produce Agent-engineering-positioned X content packs with evidence review, quality chain, reusable assets, and image assets.",
"category": "content",
"keywords": ["github", "x", "twitter", "content", "image-generation"]
},
{
"name": "searchpo",
"source": "./plugins/searchpo",
"description": "OSS Radar search pipeline: data prep, agent harness, research/impl agents, and the searchpo-full-flow command.",
"category": "research",
"keywords": ["search", "oss-radar", "pipeline", "agents"]
},
{
"name": "mcp-creator-growth",
"source": {
"source": "github",
"repo": "SunflowersLwtech/mcp_creator_growth"
},
"description": "Context-aware learning sidebar for AI coding assistants, served as an MCPThe plugins it lists here
This marketplace lists 6 plugins kept in the same repository. Each has its own page, its own measurements and its own install command.
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 Changed · +7 lines 1812b3544cf2
- 11d ago Changed · +19 lines 8a53891d1e16
- 15d ago Changed · +7 lines d67c1342fb3b
- 2mo ago First seen · 59 lines scan A 18b0fe1a8ab3
sunkit marketplace is a plugin published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed yesterday), 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…
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…
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…
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.