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 taniwhaai/arai --skill contract-derivationgit clone --depth 1 https://github.com/taniwhaai/araiWrote 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/taniwhaai/arai/contract-derivation)<a href="https://agentmods.dev/skills/taniwhaai/arai/contract-derivation"><img src="https://agentmods.dev/badge/skills/taniwhaai/arai/contract-derivation/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/taniwhaai/arai/contract-derivation"><img src="https://agentmods.dev/badge/skills/taniwhaai/arai/contract-derivation.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 | $0.00134 | $0.04657 |
| Opus 5 | $0.00067 | $0.02329 |
| Sonnet 5 | $0.00027 | $0.00931 |
| Haiku 4.5 | $0.00013 | $0.00466 |
Grade A, and why
contract-derivation 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract Derivation
Take a design document and produce a set of per-module contracts (manifests) that are complete in isolation. Each manifest must let an implementor build its module correctly without seeing any other part of the system.
Why this skill exists
A design document captures the system's structure, but its module contracts often lean on shared context — adjacent modules, the system's purpose, implicit assumptions a human reader would fill in. Compartmentalised implementation cannot rely on any of that. The implementor of one module sees only the manifest for that module, and nothing else. Anything the manifest fails to state will either be guessed (badly) or surfaced as a re-raise.
This skill's job is to take each module's contract from the design doc and harden it: make every implicit assumption explicit, name every behavioural guarantee, define every error mode, and lock down every data shape it references. The resulting manifests are the durable source of truth for the rest of the build.
Process
1. Read the design doc end to end first, and read the structural tier
Before deriving any single manifest, read the entire design doc. Each manifest will be produced in isolation, but you cannot produce them in isolation — you need the whole picture to know which assumptions are shared, which data shapes flow where, and which modules depend on which.
The design doc's "Structural tier" section shapes everything you do:
single_module: Produce one manifest. No vocabulary file is produced by default — the single module's contract names its own types inline. If you do produce a vocabulary file (only when the brief specifically names types as part of an external interface), every entry MUST besharing: local; nosharing: sharedentries are valid for single-module projects. No composition tree. See step 3 for the strict rule.small_multi_module: Produce 2–4 manifests plus one vocabulary file. Step 3 (catalogue shared vocabulary) runs as written. The composition layer above will be a single composition; sharing markers matter for the types that flow across the module boundary.full_decomposition: Produce 5+ manifests plus a full vocabulary. All steps run as written. Sharing markers are critical because the composition tree is deep.
What ships with it
4 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 · 258 lines · 134 tokens per session scan A aed79e88661e
contract-derivation is a skill published in the GitHub repository taniwhaai/arai (7 stars, last pushed 27d ago), licensed Apache-2.0. It adds 134 tokens to every session and 4,657 once invoked, about $0.0007 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
umbra-trust-review
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
michel-run-local-dev-stack
The canonical recipe for starting, checking, and stopping the Packmind local dev stack with Docker Compose — the single source of truth other skills and the Michel agent defer to. Covers bringing the full stack (PostgreSQL, Redis, NestJS API, React/Vite frontend on :4200, MCP server, nginx) up in the background, the…
michel-create-packmind-dataset
Seed a local Packmind instance with a realistic dataset — one organization populated with standards, commands, and skills — so an autonomous agent can exercise its own changes against lifelike data instead of an empty app. Use this whenever you need populated Packmind data to verify a change end-to-end: reproducing a…
hexagonal-architecture
Describes the hexagonal architecture (ports and adapters) used across the Packmind monorepo. This skill should be used when creating new domain packages, use cases, services, repositories, or any architectural component to follow established patterns.
blotato
Blotato social-media publishing and scheduling platform — REST API + MCP server. Publish and schedule posts across X/Twitter, TikTok, Instagram, LinkedIn, YouTube, Facebook, Threads, Pinterest, and more from a single integration. Use this skill whenever the user wants to schedule, publish, queue, or batch-post content…