mcp2agy-audit

mcp2agy-audit is a skill for Claude Code, Codex from uziii2208/mcp2agy. It costs 264 tokens per session (18,099 once invoked), scanned B, original, MIT.

A coordinator for the mcp2agy security-audit process, started with the /audit command. It links scanning, verification, reporting, and code fixing through separate helper agents.

In plain words
What is it for?
It scans a codebase for possible vulnerabilities, sends findings for confirmation, prepares security reports, and coordinates remediation.
Why use it?
It organizes the full review so suspected issues move through consistent checks before they are reported or fixed.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/uziii2208/mcp2agy/audit
Any agent
npx skills add uziii2208/mcp2agy --skill audit
Clone the repo
git clone --depth 1 https://github.com/uziii2208/mcp2agy

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp2agy-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/uziii2208/mcp2agy/audit.svg)](https://agentmods.dev/skills/uziii2208/mcp2agy/audit)
Your own site
<a href="https://agentmods.dev/skills/uziii2208/mcp2agy/audit"><img src="https://agentmods.dev/badge/skills/uziii2208/mcp2agy/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 264 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00264 $0.18099
Opus 5 $0.00132 $0.09050
Sonnet 5 $0.00053 $0.03620
Haiku 4.5 $0.00026 $0.01810

Measured 4d ago against content hash 2baefca811c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

mcp2agy-audit scanned grade B with 3 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 4d 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

- **Core Defect**: Outbound HTTP clients fetching user-controlled URLs without resolving IP addresses, allowing access to internal cloud metadata endpoints (`169.254.169.254`) and loopback services.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Core Defect**: Malicious `postinstall`/`preinstall` hooks with curl/wget/bash (RCE on `npm install`), dependency confusion (internal package names leaked to public registry), prototype pollution gadget chains.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

"Prompt": "Execute Phase 0-2 0day Vulnerability Scan on target files.\nRun ID: <run_id>\nTarget Files: <file_paths>\nPriority: P0-P3\n\nInstructions:\n1. Audit ALL high-yield vulnerability classes:\n P0: Shell escape con
.agents/plugins/mcp2agy/skills/audit/SKILL.md · 1,025 lines

How it starts

The opening of the file, as written. The whole thing — 1,025 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit — Multi-Agent 0day Audit Pipeline Orchestrator (v4.0.0)

🏛️ PART 1: MULTI-AGENT ORCHESTRATION & INTER-AGENT COORDINATION PROTOCOL

1.1 Master Conductor Prime Directive

You are the Master Pipeline Conductor for the mcp2agy security suite in Antigravity. You orchestrate specialized subagents to perform end-to-end vulnerability research with systematic precision:

                               ┌───────────────────────────┐
                               │   Master Audit Conductor  │
                               │        (/audit)           │
                               └─────────────┬─────────────┘
                                             │
      ┌──────────────────────────────────────┼──────────────────────────────────────┐
      │ Phase 1: SCAN                        │ Phase 2: VERIFY                      │ Phase 3: REPORT & FIX
      ▼                                      ▼                                      ▼
┌──────────────┐                       ┌──────────────┐                       ┌──────────────┐
│   Scanner    │──[candidates.yaml]───►│  Verifier(s) │──[verified.yaml]─────►│ Reporter  & │
│   Subagent   │                       │  (Parallel)  │                       │ Fixer Agents │
└──────────────┘                       └──────────────┘                       └──────────────┘
      │                                      │                                      │
[Gate 1: AST/Hash]                     [Gate 2: PoC/CVSS]                     [Gate 3: Diff/Test]

Core Invariant Directives:

  1. Never do monolithic single-agent analysis: Always delegate specialized phases to subagents via invoke_subagent.
  2. Never skip an Integrity Gate at any phase boundary.
  3. Enforce the One-Way Information Valve: Pass strictly what each downstream subagent requires.
  4. Parallel Verification: When the Scanner discovers multiple candidates, spawn concurrent Verifier subagents in the Subagents array of invoke_subagent.
  5. Cross-Platform OS Awareness: Detect host environment (Linux, macOS, Windows) and adapt pathing, permission commands, and PoC harnesses.

Read the full file on GitHub · 1,025 lines

Changes

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.

  1. 4d ago First seen · 1,025 lines · 264 tokens per session scan B 2baefca811c8

Subscribe to this mod's changes

mcp2agy-audit is a skill published in the GitHub repository uziii2208/mcp2agy (1 stars, last pushed 5d ago), licensed MIT. It adds 264 tokens to every session and 18,099 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 3 findings (cloud metadata endpoint, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens