verify-spec

verify-spec is a skill for Claude Code from kotaroyamame/formal-agent-contracts. It costs 192 tokens per session (7,110 once invoked), scanned A, original, MIT.

A checker for VDM-SL, a formal language used to describe software designs precisely. It checks the file’s grammar and types, reviews related design documents, and creates proof obligations—conditions that still need to be proven.

In plain words
What is it for?
Use it to check `.vdmsl` files, validate types and contracts, review `PROTOCOL.md` and `API-SIGNATURES.md`, and generate proof obligations.
Why use it?
It finds mistakes and inconsistencies in a specification before they become implementation problems. It also shows which parts require formal proof.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the formal-agent-contracts plugin — 15 skills shipped together

Good fit Use it to check .vdmsl files, validate types and contracts, review PROTOCOL.md and API-SIGNATURES.md, and generate proof obligations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kotaroyamame/formal-agent-contracts/verify-spec
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.

Any agent
npx skills add kotaroyamame/formal-agent-contracts --skill verify-spec
Clone the repo
git clone --depth 1 https://github.com/kotaroyamame/formal-agent-contracts

Made for: Claude Code.

Or install formal-agent-contracts, the plugin that ships this one along with the rest of its 15 skills.

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-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/verify-spec/github.svg)](https://agentmods.dev/skills/kotaroyamame/formal-agent-contracts/verify-spec)
Your own site
<a href="https://agentmods.dev/skills/kotaroyamame/formal-agent-contracts/verify-spec"><img src="https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/verify-spec/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 verify-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/kotaroyamame/formal-agent-contracts/verify-spec"><img src="https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/verify-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,110 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 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 5.1 $0.00192 $0.07110
Opus 5 $0.00096 $0.03555
Sonnet 5 $0.00038 $0.01422
Haiku 4.5 $0.00019 $0.00711

Measured 12d ago against content hash e3400a12c6d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

verify-spec 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 12d 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.

skills/verify-spec/SKILL.md · 720 lines

How it starts

The opening of the file, as written. The whole thing — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.

仕様検証スキル (v2.0.0)

VDM-SL仕様ファイルの構文チェック、型チェック、証明責務(PO: Proof Obligation)生成を実行し、開発者にわかりやすく結果を報告するスキルです。v2.0.0ではプロトコル層の整合性検証が追加されています。

概要

VDM-SLで記述された形式仕様は、以下の複数のレベルで検証が必要です:

  1. 構文検証:VDM-SL文法に従っているか
  2. 型チェック:型参照、型不整合がないか
  3. 不変式検証:不変式が一貫しているか
  4. 契約検証:前提条件と後提条件の整合性
  5. 設計文書の完全性検証(新v2.0.0):PROTOCOL.md、API-SIGNATURES.mdの内容の完全性と矛盾確認
  6. 証明責務生成:形式証明が必要な条件を生成

このスキルはVDMJツール(ISO VDM-SLの標準実装)を使用して、これらの検証を自動実行します。

ステップ1:検証ファイルの指定

目的:検証対象のVDM-SLファイルを特定

ユーザーに以下の情報を聞き出します:

  • ファイルパス:検証するVDM-SLファイル(.vdmsl形式)
  • モジュール名:検証対象のモジュール(例:HybridJudgeAgent
  • 検証範囲:全モジュール / 特定の関数のみ
  • 既存の検証結果:過去に検証したことがあるか、前回のエラーは何か

質問例

検証するVDM-SLファイルを教えてください:
形式:ファイルパスまたはファイル名
例:/path/to/agents/HybridJudgeAgent.vdmsl

ステップ2:構文検証

目的:VDM-SL文法に従っているか確認

VDMJツールの構文チェッカーを実行し、以下を検証:

  • キーワード(module, exports, definitions等)の正確性
  • 型定義の文法(Record ::, = ... |等)
  • 関数定義の文法(pre/postキーワード)
  • クォーテーション(<,>の対応)
  • コメント(--)の形式

報告内容

構文検証結果
=============
✓ ファイル: /path/to/agents/HybridJudgeAgent.vdmsl
✓ エンコーディング: UTF-8
✓ 行数: 245行

✓ 構文チェック: PASSED

詳細:
- module定義: ✓
- 型定義: ✓ (8個の型を検出)
- 関数定義: ✓ (5個の関数を検出)
- pre/post条件: ✓

エラー例

❌ 構文エラー (行127, 列14):
  予期しないトークン: 'def' の代わりに 'definitions' が必要
  
  126: export all
  127: defs
       ^^^^
  128:   Score = nat1
  
修正:'defs' → 'definitions'

ステップ3:型チェック

目的:型の定義と参照の整合性を確認

VDMJツールの型チェッカーを実行し、以下を検証:

  • 全ての型参照が定義されているか
  • 型の構造が一貫しているか
  • 関数のシグネチャが正しいか
  • 不変式の型が正しいか

報告内容

型チェック結果
==============
✓ ファイル: HybridJudgeAgent.vdmsl

✓ 型チェック: PASSED

検出された型:
  [1] Score = nat1
  [2] Threshold = nat1
  [3] Action = <AutoReply> | <OperatorAndLLM> | <OperatorOnly>
  [4] Ticket = ::
       - id: nat1
       - title: seq of char
       - content: seq of char
       - priority: nat0
       - complexity_score: Score

関数シグネチャ:
  [1] decide : Ticket -> Score -> Score -> Action
  [2] scoreAll : (seq of Score) -> seq of Score
  [3] explain_decision : (Score * Score * Score * Action) -> seq of char

Read the full file on GitHub · 720 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 720 lines · 192 tokens per session scan A e3400a12c6d9

Subscribe to this mod's changes

verify-spec is a skill published in the GitHub repository kotaroyamame/formal-agent-contracts (1 stars, last pushed 2mo ago), licensed MIT. It adds 192 tokens to every session and 7,110 once invoked, about $0.0010 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 2026-08-31.

Related

Other skills, from other repositories

verify-gates

Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…

Arch1eSUN/Arcgentic · 75 tokens

auto-loop

TDD-based autonomous development loop with checkpoint recovery and observability changelog.

claude-world/director-mode-lite · 17 tokens

workflow

Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.

claude-world/director-mode-lite · 52 tokens

test-runner

Test execution reference: framework detection (pytest/jest/vitest/go/cargo/junit) and correct run/coverage commands, plus failure-analysis steps. Use when running tests, analyzing test failures, or verifying coverage after code changes.

claude-world/director-mode-lite · 50 tokens

test-first

Drive one feature through a strict TDD Red-Green-Refactor cycle with checklists for each phase. Use when implementing new functionality test-first, or when the user runs /test-first.

claude-world/director-mode-lite · 42 tokens

linked-intent-dev

Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…

jszmajda/lid · 87 tokens