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.
npx skills add uziii2208/mcp2agy --skill verifygit clone --depth 1 https://github.com/uziii2208/mcp2agyWrote 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.
[](https://agentmods.dev/skills/uziii2208/mcp2agy/verify)<a href="https://agentmods.dev/skills/uziii2208/mcp2agy/verify"><img src="https://agentmods.dev/badge/skills/uziii2208/mcp2agy/verify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/uziii2208/mcp2agy/verify"><img src="https://agentmods.dev/badge/skills/uziii2208/mcp2agy/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.02239 |
| Opus 5.5 | $0.00037 | $0.00896 |
| Sonnet 5.5 | $0.00019 | $0.00448 |
| Haiku 4.5 | $0.00009 | $0.00224 |
Grade A, and why
mcp2agy-verify 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 2mo 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.
sink: "app/executor.py:120 (subprocess.Popen(..., shell=True))" How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify — Vulnerability Verifier & PoC Rigor Engine (v3.0.0)
0. Prime Directive & Operating Discipline
Converting suspicion into confirmed 0day vulnerabilities requires absolute empirical proof. A finding is NOT verified until:
- Source-to-sink reachability is proven with executable data-flow traces.
- All 7 confounder classes are cleared (no dead code, no implicit sanitizers, default configs).
- A deterministic Minimum Trigger Surface (MTS) PoC fires in ≤ 60 seconds in a clean environment.
- CVSS v3.1 is calibrated with empirical evidence for every metric deduction.
Operating Modes:
- Subagent Mode (Delegated by Orchestrator):
- Receives candidates from
mcp2agy_workspace/auditor_zone/results/<run_id>/candidates.yaml. - Executes deep PoC verification for assigned candidates (supports parallel instantiation per candidate).
- Writes evidence bundles to
mcp2agy_workspace/auditor_zone/results/<run_id>/evidence/<CAND_ID>/. - Writes/appends results to
mcp2agy_workspace/auditor_zone/results/<run_id>/verified_findings.yaml. - Communicates status (
CONFIRMED/FALSE-POSITIVE/UNVERIFIED-CONFOUNDER) back to Orchestrator.
- Receives candidates from
- Standalone Mode (CLI
/verify <candidate.yaml>):- Verifies candidate, creates PoC harness, outputs verdict and CVSS score.
1. Verified Finding Record Schema (verified_findings.yaml)
---VERIFIED-FINDING---
candidate_id: CAND-<run_id>-<seq>
status: CONFIRMED | FALSE-POSITIVE | UNVERIFIED-CONFOUNDER
cwe_confirmed: CWE-N
cvss_vector: "AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H"
cvss_score: 9.8
cvss_rationale: >
AV:N (network accessible via HTTP API), AC:L (no non-default config),
PR:N (unauthenticated), UI:N (no victim interaction), S:U (local process context),
C:H/I:H/A:H (arbitrary command execution as service user).
reachability_proof:
source: "app/routes.py:45 (req.params['cmd'])"
sink: "app/executor.py:120 (subprocess.Popen(..., shell=True))"
hops: ["handle_request", "sanitize_or_pass", "execute_cmd"]
interstitial_sanitizers: "NONE (grep verified)"
mts_trigger_surface:
poc_script: "evidence/<CAND_ID>/mts_poc/poc.py"
poc_command: "python evidence/<CAND_ID>/mts_poc/poc.py"
expected_output: "uid=0(root) gid=0(root)"
execution_time_seconds: 1.2
confounder_clearance:
C1_dead_code: PASS
C2_implicit_sanitizer: PASS
C3_config_gate: PASS
C4_auth_gate: PASS
C5_version_mismatch: PASS
C6_platform_constraint: PASS
C7_prior_partial_fix: PASS
blast_radius:
affected_versions: ">= 1.0.0"
fixed_in: "unfixed"
chain_feasibility:
chains_with: <CAND-id or null>
chain_role: <leg1_enabler | leg2_sink | standalone>
false_positive_reason: <required if status=FALSE-POSITIVE>
---END-VERIFIED-FINDING---
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.
- 2mo ago First seen · 179 lines · 93 tokens per session scan A 8e52ce920386
mcp2agy-verify is a skill published in the GitHub repository uziii2208/mcp2agy (1 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 2,239 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…