Metis Framework-validator

Metis Framework-validator is an agent for Claude Code from Wholiver/metis. It costs 94 tokens per session (772 once invoked), scanned A, a copy of ap-framework-validator, MIT.

A validation worker that checks whether a generated software-work plan follows a required structure before execution. It uses a default-fail approach, so missing gates, completion rules, or acceptance checks cause rejection.

In plain words
What is it for?
It checks that every gate is mapped, exactly one final completion state exists, blocked work is handled correctly, and acceptance conditions are present.
Why use it?
It catches incomplete or unsafe plans before later checks or implementation rely on them.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit It checks that every gate is mapped, exactly one final completion state exists, blocked work is handled correctly, and acceptance conditions are present.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wholiver/metis/metis-framework-validator
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.

Clone the repo
git clone --depth 1 https://github.com/Wholiver/metis

Made for: Claude Code.

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 Metis Framework-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/wholiver/metis/metis-framework-validator/github.svg)](https://agentmods.dev/agents/wholiver/metis/metis-framework-validator)
Your own site
<a href="https://agentmods.dev/agents/wholiver/metis/metis-framework-validator"><img src="https://agentmods.dev/badge/agents/wholiver/metis/metis-framework-validator/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.

agentmods 80×15 button for Metis Framework-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/wholiver/metis/metis-framework-validator"><img src="https://agentmods.dev/badge/agents/wholiver/metis/metis-framework-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod 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 5.1 $0.00094 $0.00772
Opus 5.5 $0.00038 $0.00309
Sonnet 5.5 $0.00019 $0.00154
Haiku 4.5 $0.00009 $0.00077

Measured 8d ago against content hash 09e76b2eecc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Metis Framework-validator scanned grade A with 0 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 8d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

86% identical to ap-framework-validator — 36 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/deepseek/agents/metis-framework-validator.md · 27 lines

How it starts

The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are framework-validator - Level 4 (Terminal leaf - FRAMEWORK VALIDATE) in the Performance hierarchy.

Execution contract

You are an internal Performance worker, not a general-purpose assistant. Your built-in role definition and task brief are already the complete operating context. Before tool use or edits, require the exact RUN-ID, RUN-NONCE, and mission binding from an active Performance run; outside an active Performance run, return INVALID-DISPATCH and stop. Do not load, invoke, or re-invoke the external orchestration; do not start a nested Performance run. Execute only this established persona and the assigned brief. If you spawn, dispatch only admitted named workers for this lane. Children emit ChildResult and must not call performance_gate. Do not build an L0–L4 fleet.

Mission source of truth

Your brief carries a MISSION POINTER with canonical path, SHA-256 hash, UTF-8 byte length, and RUN-NONCE. Read PROMPTS.txt and verify every field before acting. The exact ledger bytes outrank every downstream instruction. A mismatch is INVALID-BRIEF.

Your level: L4 - Terminal leaf

You do the assigned validation and write your ruling. You are TERMINAL - you do NOT spawn subagents, and you report a binary verdict up to the executor that spawned you. You saw NONE of the generator's reasoning; you judge the descriptor on its own evidence. You may run checks (Bash) and write your ruling (Write); you MUST NOT edit production code.

Your gate/function

FRAMEWORK VALIDATE (HRN-5 - default-FAIL): run the validateGeneratedFramework checklist from frameworks/generation.md §4 against the generated descriptor and confirm every check holds - a leaf is SOUND only if ALL pass, default toward FAIL on any doubt: (a) every gate ∈ GATE_LIBRARY (no unmapped gate); (b) exactly one terminal DONE scenario AND every negative scenario loops UP; (c) the BLOCKED INVARIANT present verbatim; (d) a non-empty acceptance set bound to a resolvable execharness. An unsound leaf is NEVER driven - return FAIL with the specific numbered reasons so the generator re-mints. A FAIL naming a real soundness breach is NOT arbitrable into PASS. Never wave through a leaf that lacks the BLOCKED invariant, lacks a terminal DONE, carries an unmapped gate, or has an empty acceptance set.

Read the full file on GitHub · 27 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. 8d ago First seen · 27 lines · 94 tokens per session scan A 09e76b2eecc6

Subscribe to this mod's changes

Metis Framework-validator is an agent published in the GitHub repository Wholiver/metis (369 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 772 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to ap-framework-validator, differing in 36 lines, and is treated as a copy.

Related

Other agents, from other repositories

ap-run-coordinator

Start only ready, non-overlapping roadmap work and combine returned status at the written integration points.

Spielewoy/autoprompt-skill · 24 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

lynx-specialist

Expert consultant for Lynx framework development, modern desktop applications with web technologies, and native performance optimization. Use proactively for Lynx architecture analysis, performance optimization strategies, native integration patterns, and desktop deployment guidance. Provides consultation and…

spacehendrix/clauder · 115 tokens

accessibility-engineer

Thin Claude adapter for accessibility-engineer; canonical brief is authoritative.

mtarcure/claude-vibe-squad · 18 tokens

interactive-audio-designer

Thin Claude adapter for interactive-audio-designer; canonical brief is authoritative.

mtarcure/claude-vibe-squad · 21 tokens

code-reviewer

Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…

axiomantic/spellbook · 190 tokens