export-human-spec

export-human-spec is a skill for Claude Code from kotaroyamame/formal-agent-contracts. It costs 212 tokens per session (2,934 once invoked), scanned A, original, MIT.

A tool that turns a VDM-SL formal specification into a plain-language Markdown document. VDM-SL is a precise notation for describing software data, rules, and operations.

In plain words
What is it for?
Use it to explain types, invariants, preconditions, postconditions, and operations in documents that people without VDM-SL knowledge can review.
Why use it?
Formal specifications can be difficult for non-specialists to read. A readable version lets domain experts, project managers, testers, new team members, and compliance reviewers check the same rules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

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

Good fit Use it to explain types, invariants, preconditions, postconditions, and operations in documents that people without VDM-SL knowledge can review.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kotaroyamame/formal-agent-contracts/export-human-spec"><img src="https://agentmods.dev/badge/skills/kotaroyamame/formal-agent-contracts/export-human-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,934 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 $0.00212 $0.02934
Opus 5 $0.00106 $0.01467
Sonnet 5 $0.00042 $0.00587
Haiku 4.5 $0.00021 $0.00293

Measured 10d ago against content hash cc1e3726697a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

export-human-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 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.

skills/export-human-spec/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exporting VDM-SL Specifications to Human-Readable Documents

Read a VDM-SL specification and produce a structured, clear natural language document that domain experts and non-technical stakeholders can review and understand.

VDM-SL仕様を読み取り、ドメインエキスパートや非技術者が理解・レビューできる 構造化された自然言語仕様書を生成する。

Why This Skill Exists

Formal specifications are precise but opaque to most stakeholders. In practice, formal specs need a "human-facing twin" — a document that says the same things in natural language so that:

  • Domain experts can verify the spec matches business reality
  • Project managers can understand scope and constraints
  • QA teams can derive test scenarios from readable rules
  • New team members can onboard without learning VDM-SL
  • Compliance/legal can review business logic for regulatory conformance

This skill bridges formal precision and human accessibility. The generated document is not a simplification — it's a faithful translation that preserves all information while making it readable.

Dialogue Flow

Step 1: Read the VDM-SL Specification

Ask the user for the .vdmsl file path (or find it in the workspace).

Parse and catalog the specification elements:

  • Modules — How many, what are they named
  • Types — Record types, union types, aliases, with their invariants
  • State — State variables, initialization, state invariants
  • Functions — Pure functions (side-effect free)
  • Operations — State-mutating operations with pre/post-conditions
  • Values — Named constants

Report what was found:

📄 Specification Analysis: bank-account.vdmsl

Modules:      1 (BankAccount)
Types:        4 (Account, AccountId, Money, TransferResult)
State:        1 (BankSystem with 2 variables)
Invariants:   3
Operations:   5 (Deposit, Withdraw, Transfer, GetBalance, CloseAccount)
Pre-conditions: 4
Post-conditions: 5
Functions:    1 (CalculateInterest)

Step 2: Ask About Output Preferences

Before generating, clarify what the user needs. Different audiences need different levels of detail. Use AskUserQuestion:

Read the full file on GitHub · 345 lines

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. 10d ago First seen · 345 lines · 212 tokens per session scan A cc1e3726697a

Subscribe to this mod's changes

export-human-spec is a skill published in the GitHub repository kotaroyamame/formal-agent-contracts (1 stars, last pushed 2mo ago), licensed MIT. It adds 212 tokens to every session and 2,934 once invoked, about $0.0011 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

incident

Incident response and postmortem generation from git/deploy context. When something breaks in production, this skill builds a timeline, identifies the probable cause, and generates a structured postmortem document. Flags: --since, --service, --sev, --revert, --comms, --dry-run.

greglas75/zuvo · 64 tokens

presentation

Generate PowerPoint (PPTX) presentations from a topic, outline, or content file. Creates professional slides using python-pptx with consistent theming and typography. Modes: [topic] (from scratch), from [file] (from markdown), --slides N, --theme dark|light|corporate, --outline-only, --out [path], --lang [code].

greglas75/zuvo · 80 tokens

knowledge-curation

Process a source document (functional spec, technical doc, ADR, meeting notes, interview, workshop, glossary) into curated knowledge under /knowledge. Use when asked to curate, extract, decompose, or structure a business document, or when curation is mentioned alongside a file path or attachment or a non-document…

DiUS/agent-toolkit · 102 tokens

skill-doc-delivery

Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.

nyldn/claude-octopus · 29 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

meeting-notes

Use when a meeting just ended and a transcript or rough notes must become a record the absent can act on — decisions with their why, actions with an owner and a real date, open questions, a recap inside 24–48h — or to clean an AI-notetaker draft that invented tasks or swapped speakers. NOT the durable ADR with…

ericrisco/rsc-harness · 82 tokens