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 reconcile-codegit 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/reconcile-code)<a href="https://agentmods.dev/skills/kotaroyamame/formal-agent-contracts/reconcile-code"><img src="https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/reconcile-code/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/reconcile-code"><img src="https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/reconcile-code.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 | $0.00089 | $0.05028 |
| Opus 5 | $0.00044 | $0.02514 |
| Sonnet 5 | $0.00018 | $0.01006 |
| Haiku 4.5 | $0.00009 | $0.00503 |
Grade A, and why
reconcile-code 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 9d 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 — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconcile Code Skill
Overview / 概要
This skill reconciles existing code with a confirmed VDM-SL specification through systematic comparison, generates diff reports, produces prioritized code fixes, and auto-generates comprehensive tests.
このスキルは、確認済みのVDM-SL仕様との間で既存コードを体系的に比較し、差分レポートを生成し、優先度付きコード修正を生成し、包括的なテストを自動生成します。
Step 1: Item-by-Item Comparison
Type Definitions
EN: For each VDM-SL type definition in the confirmed spec, locate the corresponding code type (TypeScript interface/type, Python dataclass, etc.):
- Verify all field names match spec exactly
- Verify all field types match spec types (accounting for language-specific representations)
- Verify optional/required markers match (nullable, Optional[], etc.)
- Check for extra fields in code not in spec
- Check for missing fields in code that are in spec
JP: 確認済み仕様のVDM-SL型定義ごとに、対応するコード型(TypeScriptインターフェース/型、Pythonデータクラスなど)を見つけます:
- すべてのフィールド名が仕様と正確に一致することを確認
- すべてのフィールド型が仕様型と一致することを確認(言語固有の表現を考慮)
- オプション/必須マーカーが一致することを確認(nullable、Optional[]など)
- 仕様にない仕様にないコード内の余分なフィールドをチェック
- 仕様にあるがコードにない欠落フィールドをチェック
Status Codes:
- ✅ Match: All fields present, types correct, required/optional markers align
- ⚠️ Partial: Some fields missing/extra, or minor type representation differences that don't affect runtime
- ❌ Mismatch: Type definitions are incompatible, will cause runtime errors
- 🔍 Not Found: No corresponding type found in code
Pre-conditions
EN: For each VDM-SL pre-condition (guards in the function specification), find the corresponding code implementation:
- Look for guard clauses, early returns with error checks, parameter validation
- Verify the guard logic is equivalent to the pre-condition
- Check that appropriate errors/exceptions are thrown on violation
- Identify if the guard is implicit (e.g., type system enforces) or explicit (runtime check)
JP: VDM-SL仕様の各前提条件(関数仕様のガード)について、対応するコード実装を見つけます:
- ガード句、エラーチェック付きの早期リターン、パラメータ検証を探す
- ガードロジックが前提条件と等価であることを確認
- 違反時に適切なエラー/例外がスロウされることを確認
- ガードが暗黙的(型システムが強制)か明示的(実行時チェック)かを識別
What ships with it
2 files 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.
- 9d ago First seen · 554 lines · 89 tokens per session scan A 24cc4dc63627
reconcile-code is a skill published in the GitHub repository kotaroyamame/formal-agent-contracts (1 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 5,028 once invoked, about $0.0004 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
audit-round
External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaitingaudit or auditinprogress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDSFIX / AUDITINCOMPLETE…
code-reviewer
Code review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.
arrow-maintenance
Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…
reviewer
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.
db-audit
Database performance and safety audit. 70+ checks across 13 dimensions (DB1-DB13): query patterns, indexes, schema design, connections, transactions, migrations, caching, query optimization, ORM anti-patterns, observability, data lifecycle, DB security, and migration deployment safety. Code-level checks for all ORMs.…