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.
/plugin marketplace add SunflowersLwtech/sunkitnpx agentmods add plugins/sunflowerslwtech/sunkit/search-harnessgit clone --depth 1 https://github.com/SunflowersLwtech/sunkitGrade A, and why
search-harness 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 12 lines scan A 01bdca3187f4
search-harness is a plugin published in the GitHub repository SunflowersLwtech/sunkit (13 stars, last pushed 1mo ago), with no licence file. 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
designer-skill
Plug-and-play MCP that gives your agent UI superpowers. One install: design skill + MCP server, zero config.
moyu marketplace
moyu. 🐟 狠狠 PUA 你的 AI，然后自己准时下班。Make your AI grind, so you don't have to. Benchmarked: 66% less code.
rashomon
Evaluate prompts and skills through parallel execution comparison in git worktrees. Prompt optimization with BP-001009 patterns, skill creation/update with quality grading, and blind A/B evaluation.
opus-pocus
🪄 Wave wand over repo. Curses removed. Opus behaves. Spells that de-hex your Claude instructions for the Opus 5 era — remove verify-your-work incantations, death-spiral hooks, vague rules that summon demons, and automation that lies about its own state.
prompt-improver
Turn vague agent prompts into precise, verifiable XML specs — then execute or plan. Headless multi-CLI generator. Use when the user says improve prompt, plan carefully, or structure a vague coding request.
n2-fieldops
A multi-runtime FieldOps suite with 17 evidence-driven skills for Claude Code, Codex, Kimi, and CC Switch.