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 design-docgit 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/design-doc)<a href="https://agentmods.dev/skills/taniwhaai/arai/design-doc"><img src="https://agentmods.dev/badge/skills/taniwhaai/arai/design-doc/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/design-doc"><img src="https://agentmods.dev/badge/skills/taniwhaai/arai/design-doc.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 | $0.00137 | $0.05023 |
| Opus 5 | $0.00068 | $0.02511 |
| Sonnet 5 | $0.00027 | $0.01005 |
| Haiku 4.5 | $0.00014 | $0.00502 |
Grade A, and why
design-doc 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Doc
Produce a structural design document that commits to the shape of a system before any code is written. The document is the seed artefact for everything downstream — contract derivation, leaf implementation, and composition all read from it.
Why this skill exists
When code generation begins without an explicit structural commitment, each step optimises locally. A class is added here, a wrapper there, a "just in case" abstraction somewhere else. There is no global view to push back against any individual decision, so the codebase accretes complexity that nobody asked for and nobody can later justify.
A design document forces the global decisions to happen first, in one place, where they can be evaluated against each other. Once it exists, every subsequent generation step has a constraint to honour rather than a blank canvas to sprawl across. The discipline is the value; the document is the artefact that carries it.
This is not a UML diagram and it is not a README. It is the smallest artefact that can fully answer: what modules exist, what is each one responsible for, what does each one expose, and how does data flow between them.
When to produce a design doc
Produce one whenever the work is larger than a single function or single file change. The cost of the document is small; the cost of an unconstrained generation that has to be unwound later is large.
Skip it for: bug fixes scoped to one module, single-file scripts, experimental throwaway code the user has explicitly framed as throwaway, or modifications that fit entirely within an existing module's contract.
The single most important rule
If the prompt under-specifies a behaviour, ask. Do not decide.
The most expensive failure mode of this skill is silently filling in plausible-looking detail that the user never asked for. A prompt like "build me a URL shortener" does not specify retry counts, consistency policies, or the exact shape of given external interfaces — and those are not decisions for you to make. They are decisions for the user. Picking a "reasonable" value for any of them buries a tradeoff in the design that the user never agreed to and that downstream agents will faithfully implement.
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 · 288 lines · 137 tokens per session scan A 1c4733bdfef5
design-doc is a skill published in the GitHub repository taniwhaai/arai (7 stars, last pushed 27d ago), licensed Apache-2.0. It adds 137 tokens to every session and 5,023 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…