mcp2agy-status

mcp2agy-status is a skill for Claude Code, Codex from uziii2208/mcp2agy. It costs 65 tokens per session (1,164 once invoked), scanned A, original, MIT.

A status monitor for the security-audit pipeline and its worker agents. It checks the host environment, running tasks, audit phases, findings, and generated files.

In plain words
What is it for?
Checking subagent activity, tracking scans and verification runs, counting findings, inspecting pipeline progress, and reviewing available audit files.
Why use it?
It provides a single view of what is running, what has finished, and which audit results or artifacts exist.

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/status
Any agent
npx skills add uziii2208/mcp2agy --skill status
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-status

README.md
[![agentmods](https://agentmods.dev/badge/skills/uziii2208/mcp2agy/status.svg)](https://agentmods.dev/skills/uziii2208/mcp2agy/status)
Your own site
<a href="https://agentmods.dev/skills/uziii2208/mcp2agy/status"><img src="https://agentmods.dev/badge/skills/uziii2208/mcp2agy/status.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,164 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00065 $0.01164
Opus 5 $0.00032 $0.00582
Sonnet 5 $0.00013 $0.00233
Haiku 4.5 $0.00006 $0.00116

Measured 3d ago against content hash df2b3dc09cb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp2agy-status scanned grade A with 1 finding 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 3d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Permission hardening mechanism (`chmod 600` vs `icacls`)

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

.agents/plugins/mcp2agy/skills/status/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/status — Pipeline Status & Multi-Agent Workspace Monitor (v3.5.0)

0. Overview

The Status module aggregates live multi-agent execution state, host OS environment details, background tasks, and artifact inventories across all mcp2agy modules.


1. Inspection Routine

When /status is executed:

Step 1: Detect Host Environment & OS

Detect the platform context (or invoke detect_platform MCP tool):

  • Operating System (Windows, Linux, macOS)
  • Architecture & Shell environment (powershell, cmd, bash, zsh)
  • Permission hardening mechanism (chmod 600 vs icacls)

Step 2: Query Live Subagents

Execute manage_subagents(Action="list") to inspect all active direct subagents:

  • Identify running, idle, or waiting subagents.
  • Track current task summaries and conversation IDs.

Step 3: Inspect Workspace Runs

Scan mcp2agy_workspace/auditor_zone/results/:

  • Enumerate run directories (YYYYMMDD_HHMMSS).
  • Read pipeline_state.json (if present) to check phase progression (Scan → Verify → Report → Fix).
  • Count total candidates in candidates.yaml.
  • Count verified findings in verified_findings.yaml (CONFIRMED, FALSE-POSITIVE).
  • Check existence of report.md and fixes.diff.

Step 4: Enumerate Multi-Module Artifacts

  • Recon: Count targets in mcp2agy_workspace/recon/results/.
  • Exploits: Count PoC scripts in mcp2agy_workspace/exploits/pocs/ and chains in chains/.
  • Reverse: Count decompiled targets in mcp2agy_workspace/reverse/analysis/.
  • CTF: Count solves in mcp2agy_workspace/ctf/solves/ and captured flags in mcp2agy_workspace/loot/flags.txt.
  • Tools: Count forged tools in mcp2agy_workspace/tools/.

2. Dashboard Output Format

Render the executive status dashboard:

# 🛡️ mcp2agy — Multi-Agent Workspace Dashboard

> **Platform:** Antigravity CLI | **Version:** 3.5.0
> **Host OS:** <Linux/macOS/Windows> (<arch>, <shell>) | **User:** `<username>`
> **Workspace Root:** `mcp2agy_workspace/`

---

## 💻 Host Platform Context
| Parameter | Value | Audit Implication |
|-----------|-------|-------------------|
| **OS / Platform** | `win32` / `linux` / `darwin` | <Windows NTFS vs POSIX umask path & permission rules> |
| **Path Separator** | `\` or `/` | <Case-insensitive vs case-sensitive path traversal> |
| **Permission Primitives**| `icacls` or `chmod 600` | <Restricted file ACL enforcement> |
| **Audit Trail Log** | `~/.mcp2agy/audit.log` | Active cross-platform UTC event logging |

---

## 🤖 Active Subagent Swarm
| Role | Type | Conversation ID | State | Current Task |
|------|------|-----------------|-------|--------------|
| Repository 0day Scanner | `mcp2agy-scanner-agent` | `conv-123` | IDLE | Scan completed for src/ |
| PoC Verifier | `mcp2agy-verifier-agent` | `conv-456` | RUNNING | Verifying CAND-001 |

---

## 📊 0day Audit Pipeline Runs
| Run ID | Stage Reached | Candidates | Confirmed (CVSS) | False Positives | Artifacts |
|--------|---------------|------------|------------------|-----------------|-----------|
| `20260827_120000` | Fix Complete (Gate 4) | 4 | 2 (Crit: 1, High: 1) | 2 | [Report](file:///...) \| [Diff](file:///...) |

---

## 🗂️ Multi-Module Artifact Inventory
| Module | Directory | Count | Status |
|--------|-----------|-------|--------|
| **Audit Reports** | `auditor_zone/results/` | <N> Runs | <M> Confirmed 0days |
| **Reconnaissance** | `recon/results/` | <N> Targets | Attack surface mapped |
| **Exploit PoCs** | `exploits/pocs/` | <N> Scripts | Weaponized harnesses |
| **Reverse Engineering** | `reverse/analysis/` | <N> Targets | Decompiled & Annotated |
| **CTF Solves & Loot** | `ctf/solves/` | <N> Solved | <Flags> Flags Captured |
| **Forged Tools** | `tools/` | <N> Tools | Fuzzers & Scanners |

---
*Run `/audit <path>` to launch a full pipeline audit or `/swarm <target>` for multi-module operation.*

Read the full file on GitHub · 101 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. 3d ago First seen · 101 lines · 65 tokens per session scan A df2b3dc09cb9

Subscribe to this mod's changes

mcp2agy-status is a skill published in the GitHub repository uziii2208/mcp2agy (1 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,164 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). 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

timeline-creator

Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.

mhattingpete/claude-skills-marketplace · 47 tokens

bootstrap-prd

Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.

joshukraine/dotfiles · 25 tokens

glab-issue

Create, view, update, and manage GitLab issues. Use when working with issue tracking, bug reports, feature requests, or task management. Operations include creating issues, listing with filters, viewing details, adding comments/notes, updating labels/assignees/milestones, closing/reopening, and board management.…

vince-winkintel/gitlab-cli-skills · 89 tokens

sales-ops

Set up and run Airtable-based sales operations and CRM workflows — pipeline management, account and renewal management, deal desk, RFP / tender pipelines, partner CRMs, sales forecasting, vertical CRMs (real estate, mortgage, brokerage, capital markets, public works, nonprofit), and AI-native lean stacks…

Airtable/skills · 164 tokens

jira

Search and manage Jira issues using JQL queries, create/update tickets, and manage workflows. Use when asked to find Jira tickets, check the backlog, manage sprints, track bugs, or work with Atlassian project management.

odyssey4me/agent-skills · 48 tokens

github

Use this skill when Enoch needs to coordinate work with GitHub: branches, pull requests, issues, reviews, comments, checks, and merges.

our-ark/enoch · 0 tokens