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 dadwadw233/claude-code-harnessnpx agentmods add plugins/dadwadw233/claude-code-harness/claude-code-harnessgit clone --depth 1 https://github.com/dadwadw233/claude-code-harnessGrade A, and why
claude-code-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.
What it actually says
{
"name": "claude-code-harness",
"description": "A harness blueprint skill inspired by Claude Code-class systems.",
"version": "0.1.0",
"author": {
"name": "Yuanhong Yu",
"email": "[email protected]"
},
"homepage": "https://github.com/dadwadw233/claude-code-harness",
"repository": "https://github.com/dadwadw233/claude-code-harness",
"license": "MIT"
}
What ships with it
1 file beside plugin.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 · 14 lines scan A 86fd94b4bd3c
claude-code-harness is a plugin published in the GitHub repository dadwadw233/claude-code-harness (11 stars, last pushed 4mo 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 2026-08-30.
Other plugins, from other repositories
everruns-dev
Everruns plugins for Claude Code - connect Claude to the Everruns(Dev) managed harnesses platform to manage agents, harnesses, capabilities, sessions, and apps.
microsoft-docs
Search official Microsoft documentation, API references, and code samples for Azure, .NET, Windows, and more through the Microsoft Learn MCP server.
everruns-dev
Interact with the Everruns(Dev) managed harnesses platform. Manage harnesses, agents, and capabilities. Run agentic sessions. Create and deploy agentic applications.
everruns
Interact with the Everruns managed harnesses platform. Manage harnesses, agents, and capabilities. Run agentic sessions. Create and deploy agentic applications.
resend
Send transactional emails through the Resend remote MCP server. Connects with OAuth — no API key handling in the agent.
oauth-mail
Fixture plugin whose MCP server requires OAuth. Exercises the plugin OAuth-anchor install path. Does not point at a live server.