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 manhua-man/harness-coding-protocolnpx agentmods add plugins/manhua-man/harness-coding-protocol/marketplacegit clone --depth 1 https://github.com/manhua-man/harness-coding-protocolGrade A, and why
harness-coding-protocol 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.
What it actually says
{
"name": "harness-coding-protocol",
"owner": {
"name": "ManHua"
},
"metadata": {
"description": "IDE-first harness: install from GitHub, run /harness-init (no npm package, no terminal CLI).",
"version": "2.5.0"
},
"plugins": [
{
"name": "harness-coding-protocol",
"source": {
"source": "url",
"url": "https://github.com/manhua-man/harness-coding-protocol.git"
},
"description": "Clone or reference this repo as a Claude plugin. /harness-init grounds itself by reading repo files; the IDE_Agent reads, judges, and writes root-truth files (AGENTS.md, CLAUDE.md, steering/, Cursor adapters) after one user confirmation. No Node/npm/npx prerequisite for users.",
"version": "2.5.0",
"author": {
"name": "ManHua"
},
"keywords": [
"harness-init",
"ide-first",
"root-truth",
"run-artifacts",
"claude-adapter",
"cursor-adapter",
"protocol",
"governance"
],
"category": "workflow"
}
]
}
What ships with it
1 file beside marketplace.json 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.
- 2d ago First seen · 36 lines scan A c09cb0294408
harness-coding-protocol is a plugin published in the GitHub repository manhua-man/harness-coding-protocol (5 stars, last pushed 2d ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
superpowers-zh
AI 编程超能力中文增强版:20 个 skills(14 翻译 + 4 中国原创 + 2 上游历史保留),支持 Claude Code / Hermes Agent / Cursor / Claw Code / Qoder 等 23 款工具.
ijfw
Plugin marketplace listing 1 plugin: ijfw.
draft-plugins
Plugin marketplace listing 1 plugin: draft.
memex
Zettelkasten-based agent memory system with bidirectional links.
specops
Spec-driven development workflow - transforms ideas into structured specifications (requirements, design, tasks) before implementation.
project-brain
Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.