Governance for agent instructions: audit, score, and pin MCP servers, Agent Skills, and prompts. Deterministic; findings carry a reference and a fix.
View on GitHub ↗Tool descriptions and skill files are injected into a model's context on every request. They decide which tool gets called, with what arguments, whether the client asks before something is destroyed, and whether a skill fires at all. They are production configuration — and almost nobody reviews them, versions them, or notices when they change.
sounding audits them, scores them with a formula you can check, writes the corrections, and pins them so you find out when they drift.
------ MCP servers permission, blast radius, injection surface, transport, secrets Agent Skills triggering, progressive disclosure, dangerous commands, portability Prompts output contract, failure behaviour, interpolation safety, contradictions
They are the same problem. A skill and a tool description are both text handed to a model, living in a repo, versioned, drifting — so they share one engine and one report.
Every finding carries a reference. Not "this looks risky" — the spec section or guidance that says why. A finding without a source is an opinion, and this tool does not ship opinions.
Every finding carries a fix, or a question. When the correction is unambiguous, it says what to change. When it depends on intent the tool cannot infer, it asks — with options, capped at three per run:
And then it writes them. Answers become edits to your descriptor, shown as a diff before anything is touched:
Anything generated that still needs a human is marked TODO in the output. The tool does not write prose and present it as finished — and in a SKILL.md it rewrites the frontmatter only. Body text is y
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/alinotfoundbtw--sounding.html)
Scan MCP servers & AI-agent skills for malicious patterns (prompt injection in tool descriptions, credential exfil, download-and-execute). 17 patterns / 60 signatures, zero-dep. Measured over 196 publ
surendranb/writing-skillsProcedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character voices. Agent Plugins 1.0.0, works in openc
korovin-aa97/talkthrough-mcpMCP server: turn narrated screen recordings into agent-ready data — local Whisper transcript, scene keyframes, OCR, wall-clock anchoring. Record your screen, talk — your AI agent files the bugs.
bestdeejay-design/agent-skillsAgent Skills - 29 skills for AI agents (Sisyphus, opencode): frontend-perfection (Lighthouse audit), secret-scanner, security-review, version-bumper, commit-lint, coverage-analyzer, api-contract-testi
frangelbarrera/code-review-agent-mcpAI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.
dheerajjha/mcp-migrateFind and fix what the MCP 2026-07-28 spec revision breaks in your server. 21 rules, 5 autofixers, and a readiness board.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.