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 kensaurus/mushi-mushinpx agentmods add plugins/kensaurus/mushi-mushi/mushi-debuggergit clone --depth 1 https://github.com/kensaurus/mushi-mushiGrade A, and why
mushi-debugger 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": "mushi-debugger",
"description": "Triage and fix Mushi Mushi bug reports from inside Claude Code — reports, plain-English diagnosis, paste-ready fix context, optional fix dispatch",
"version": "1.0.0",
"author": {
"name": "kensaurus",
"url": "https://github.com/kensaurus/mushi-mushi"
},
"homepage": "https://kensaur.us/mushi-mushi/docs",
"repository": "https://github.com/kensaurus/mushi-mushi",
"license": "MIT",
"keywords": ["debugging", "bug-reports", "mcp", "triage"],
"mcpServers": "./.mcp.json"
}
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 · 15 lines scan A 93855182c096
mushi-debugger is a plugin published in the GitHub repository kensaurus/mushi-mushi (3 stars, last pushed 5d 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
ama-openapi
Skills for working with Amadeus OpenAPI specification projects - create projects, manage models, add dependencies, and configure field masks.
ama-sdk
Skills and guidance for creating, using, and extending TypeScript SDKs generated from OpenAPI specifications with @ama-sdk.
vitest-auto-spy
Plugin marketplace listing 1 plugin: vitest-auto-spy.
vitest-auto-spy
Typed test spies from a class or a type on Vitest, bun:test and node:test — the skill teaches an agent the API, the anti-patterns, the error→fix table and the jest-auto-spies migration codemod.
bugscribe
A single skill that files one already-identified bug as a new GitHub issue: verifies the defect against the source code, checks the backlog for duplicates, posts a short report pointing to a file and line, and pings the repository owner exactly once — it reports a known finding rather than searching for one.
angular-upgrade-kit
AI Agent Teams for upgrading Angular apps across ANY major version (v2→v21+). 8 specialized agents, 18 version reference files, deterministic hooks, and MCP integrations.