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 route-modelsgit 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/route-models)<a href="https://agentmods.dev/skills/kotaroyamame/formal-agent-contracts/route-models"><img src="https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/route-models/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/route-models"><img src="https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/route-models.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 | $0.00179 | $0.02503 |
| Opus 5 | $0.00089 | $0.01252 |
| Sonnet 5 | $0.00036 | $0.00501 |
| Haiku 4.5 | $0.00018 | $0.00250 |
Grade A, and why
route-models 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 10d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Routing — Contract-Driven Model Assignment per Module
Overview
Multi-agent development spends most of its tokens on bulk phases: code generation, test generation, and reconciliation. Not every module needs the strongest model for those phases — a types-only module converts mechanically, while a module full of implicit definitions needs real reasoning.
This skill reads the VDM-SL contract and assigns each module to the lightest capable model tier, using only objective, countable signals from the spec. The formal contract itself is what makes this safe: whichever model generates the artifact, the same VDMJ checks and contract tests judge the result.
マルチエージェント開発でトークンを最も消費するのは、コード生成・テスト生成・照合 といった一括処理のフェーズです。型定義だけのモジュールは機械的に変換できる一方、 暗黙的定義だらけのモジュールには本物の推論が要ります。
このスキルは VDM-SL 契約を読み取り、仕様に含まれる客観的で数えられるシグナルだけを 根拠に、各モジュールを「能力が足りる範囲で最も軽いモデル層」へ割り振ります。これが安全 なのは形式契約があるからです — どのモデルが生成しても、同じ VDMJ チェックと契約 テストが結果を判定します。
Trigger Conditions
Activate this skill when the user says any of:
- 「モデルを割り振って」「モジュールごとに軽量モデルを使いたい」
- 「トークン消費を抑えたい」「コストを下げたい(生成フェーズで)」
- "Route models", "assign models per module", "reduce token cost"
- Before a bulk generation phase over a multi-module spec, when the user wants to reduce cost
Model Tiers
Tiers are abstract; the concrete model names depend on what the runtime offers.
In Claude Code, subagents accept a model parameter — map tiers as follows:
| Tier | Claude Code model | Suited for |
|---|---|---|
| light | haiku |
Mechanical conversion: types-only modules, boilerplate, simple pure functions |
| standard | sonnet |
Typical modules: state + invariants, explicit operations |
| heavy | inherit (the session's main model) |
Implicit-definition-heavy modules, cross-module protocol logic, high PO counts |
層は抽象名で扱い、実行環境が提供するモデルに対応付けます。heavy は「セッションの
メインモデルを継承」が既定です(メインより強いモデルを勝手に選ばない)。
Execution Flow
Step 1: Read the Specification
Read the .vdmsl file(s) specified by the user (search the workspace if unspecified).
Split into modules: VDM-SL module ... end sections, or treat a flat file as one module.
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.
- 10d ago First seen · 189 lines · 179 tokens per session scan A 1bcb007368a2
route-models is a skill published in the GitHub repository kotaroyamame/formal-agent-contracts (1 stars, last pushed 2mo ago), licensed MIT. It adds 179 tokens to every session and 2,503 once invoked, about $0.0009 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
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
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.…
session-mode
Use when a project has not yet stored session mode, when a user asks for complete arcgentic workflow execution, or when role identity handoff prompts are needed.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
agency-roster
Use when a round references agency-agents catalogs, role-family routing, multi-agent identity prompts, or English/Chinese specialist role catalogs.