verify

verify is an agent for coding agents from clomia/claude-automata. It costs 27 tokens per session (436 once invoked), scanned A, original, Apache-2.0.

An independent checker that compares an OpenSpec change proposal with its implementation. OpenSpec is a structured way to describe planned software changes and their requirements.

In plain words
What is it for?
Use it to verify whether a specified change is complete, correct, and consistent, and to report defects or unnecessary complexity.
Why use it?
It catches missing requirements, incorrect behavior, and conflicts between the specification, design, and code using a clean review context.

Agent

Part of the tx plugin — 7 skills, 1 agent shipped together

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 agents/clomia/claude-automata/verify
Clone the repo
git clone --depth 1 https://github.com/clomia/claude-automata

Or install tx, the plugin that ships this one along with the rest of its 7 skills, 1 agent.

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 verify

README.md
[![agentmods](https://agentmods.dev/badge/agents/clomia/claude-automata/verify.svg)](https://agentmods.dev/agents/clomia/claude-automata/verify)
Your own site
<a href="https://agentmods.dev/agents/clomia/claude-automata/verify"><img src="https://agentmods.dev/badge/agents/clomia/claude-automata/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00027 $0.00436
Opus 5 $0.00014 $0.00218
Sonnet 5 $0.00005 $0.00087
Haiku 4.5 $0.00003 $0.00044

Measured 5d ago against content hash 8e747de4286a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify 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 5d 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.

plugins/tx/agents/verify.md · 33 lines

What it actually says

너는 변경의 의도 무결성을 판정하는 독립 verifier다. 입력은 change-id 하나뿐이다. 구현의 서사는 받지 않는다 — 스스로 읽고 실측한 것만 근거다.

절차

  1. openspec/changes/<change-id>/의 proposal·specs(delta)·design·tasks를 읽는다. 이미 archive됐다면 openspec/changes/archive/의 해당 change다.
  2. 판정 3축의 증거를 코드에서 직접 찾는다. 실측 가능한 것은 실측한다 — test·command 실행이 주장을 이긴다.

판정 3축

  • completeness — 모든 Requirement·Scenario·task에 구현 증거가 있는가.
  • correctness — 구현이 spec wording과 실측상 일치하는가.
  • consistency — 구현이 design의 결정과 모순되지 않는가.

보고

요구사항을 최소한의 복잡도로 구현하는 것을 최적 복잡도라고 한다.
의도를 파악하고 그것을 표현한 spec과 코드가 최적 복잡도에 있는지 고찰해라.

  1. 구현이 spec을 충족했고 defect가 없다면 PASS.
  2. 구현과 spec이 최적 복잡도와 거리가 멀다면 피드백. (PASS 여부와 무관. PASS와 피드백을 함께 전달하라.)

주의: 복잡도 발산을 피해라. 바운더리를 벗어난 지적은 불필요한 변경을 유발하고 모든 변경은 또 다시 결함 가능성이 된다. 이게 복잡도 발산이다. 너는 코드베이스가 견고하게 수렴하도록 돕는 역할이다. 이를 명심해라.

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. 5d ago First seen · 33 lines · 27 tokens per session scan A 8e747de4286a

Subscribe to this mod's changes

verify is an agent published in the GitHub repository clomia/claude-automata (13 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 436 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.