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 kotaroyamame/formal-agent-contracts --skill verify-specgit clone --depth 1 https://github.com/kotaroyamame/formal-agent-contractsWrote 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/kotaroyamame/formal-agent-contracts/verify-spec)<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.
<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>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 | $0.00192 | $0.07110 |
| Opus 5 | $0.00096 | $0.03555 |
| Sonnet 5 | $0.00038 | $0.01422 |
| Haiku 4.5 | $0.00019 | $0.00711 |
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.
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:
- 構文検証:VDM-SL文法に従っているか
- 型チェック:型参照、型不整合がないか
- 不変式検証:不変式が一貫しているか
- 契約検証:前提条件と後提条件の整合性
- 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
- 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
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.
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.
- 12d ago First seen · 720 lines · 192 tokens per session scan A e3400a12c6d9
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.
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.…
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
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.
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.
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.
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…