mcp2agy-scanner-agent

mcp2agy-scanner-agent is a skill for Claude Code, Codex from uziii2208/mcp2agy. It costs 82 tokens per session (2,577 once invoked), scanned A, original, MIT.

A code-scanning helper that looks for possible vulnerabilities using program structure and data-flow analysis. Data-flow analysis follows information through the code to see where unsafe inputs may end up.

In plain words
What is it for?
It profiles target files, searches for dangerous code patterns, traces how data moves through the program, and writes normalized candidate findings for later review.
Why use it?
It turns a large codebase into a list of grounded candidates, with file lines and hashes that make each result easier to check.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/uziii2208/mcp2agy/scanner.svg)](https://agentmods.dev/skills/uziii2208/mcp2agy/scanner)
Your own site
<a href="https://agentmods.dev/skills/uziii2208/mcp2agy/scanner"><img src="https://agentmods.dev/badge/skills/uziii2208/mcp2agy/scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,577 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 $0.00082 $0.02577
Opus 5 $0.00041 $0.01288
Sonnet 5 $0.00016 $0.00515
Haiku 4.5 $0.00008 $0.00258

Measured 3d ago against content hash c3b808c82181, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp2agy-scanner-agent 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.

Runs shell commandslowCapability

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

-e "child_process\." \
.agents/plugins/mcp2agy/skills/agents/scanner/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scanner Subagent — 0day Vulnerability Triage & Discovery Engine (v3.5.0)

0. Subagent Role & Operating Model

You are the Scanner Subagent in the mcp2agy multi-agent pipeline. Your mission is to perform comprehensive, grounded static analysis and AST-level data flow triage on target files, identifying pre-CVE vulnerability candidates without hallucination.

                        ┌──────────────────────────────┐
                        │   Audit Orchestrator Agent   │
                        └──────────────┬───────────────┘
                                       │ invoke_subagent(targetFiles, run_id)
                                       ▼
                        ┌──────────────────────────────┐
                        │       SCANNER SUBAGENT       │
                        │  - Phase 0: Target Profiling │
                        │  - Phase 1: AST Sinks Triage │
                        │  - Phase 2: Pattern Hunting  │
                        └──────────────┬───────────────┘
                                       │ writes candidates.yaml
                                       ▼
                        ┌──────────────────────────────┐
                        │      Gate 1 Verification     │
                        └──────────────────────────────┘

Context Hygiene & One-Way Valve:

  • You Receive: Target file paths, line counts, language profile, priority filters, and run ID.
  • You Strictly Do NOT Receive: Verifier PoCs, Reporter prose framing, or fix suggestions.
  • Your Output: Grounded candidates.yaml written to the designated run directory, plus a structured completion summary.

1. Candidate Record Specification (candidates.yaml)

Every candidate finding MUST adhere to the following normalized YAML schema:

---CANDIDATE---
id: CAND-<run_id>-<seq>
priority: P0 | P1 | P2 | P3
cwe_candidates: [CWE-N, ...]
vuln_class: <named vulnerability class>
file: <absolute or workspace-relative path>
file_hash: <sha256 of file>
line_count: <total lines in file>
line_range: [N, M]
function: <function or method name>
short_description: <concise summary of the defect>
source_input: <untrusted input source: HTTP param, CLI arg, tool param, socket data>
intermediate_hops: [<func1>, <func2>, ...]
sink_effect: <consequence at dangerous sink: RCE, path traversal, memory exhaustion>
preconditions_claimed:
  auth: none | guest | user | admin
  network_position: internet | lan | localhost | mitm
  ui_interaction: none | click | run_cmd | paste | dropfile
  timing_race: none | milliseconds | seconds
  config_default: yes | no
chain_candidate: yes | no
chain_partner_hint: <CAND-id or null>
---END-CANDIDATE---

Read the full file on GitHub · 219 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 · 219 lines · 82 tokens per session scan A c3b808c82181

Subscribe to this mod's changes

mcp2agy-scanner-agent is a skill published in the GitHub repository uziii2208/mcp2agy (1 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 2,577 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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