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 agentmods add skills/etr/groundwork/design-it-twicenpx skills add etr/groundwork --skill design-it-twicegit clone --depth 1 https://github.com/etr/groundworkWrote 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/etr/groundwork/design-it-twice)<a href="https://agentmods.dev/skills/etr/groundwork/design-it-twice"><img src="https://agentmods.dev/badge/skills/etr/groundwork/design-it-twice.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00921 |
| Opus 5 | $0.00022 | $0.00461 |
| Sonnet 5 | $0.00009 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
design-it-twice 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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design It Twice
Overview
Your first interface is rarely your best (Design it twice, Ousterhout). Before you commit a module boundary, generate genuinely different designs and compare them — the cost of exploring on paper is trivial next to the cost of a shallow interface that Hyrum's Law then freezes into a contract.
Core principle: Aim for deep modules — a simple interface hiding substantial functionality. A design that merely forwards calls is shallow and usually a liability.
This is a build-time and architecture-time discipline. [[design-architecture]] and [[swarm-design-architecture]] invoke it for module boundaries; invoke it directly any time you're about to design a single non-trivial interface.
When to Use
- A new module, service boundary, or public API
- A refactor that reshapes an existing interface many callers depend on
- Any seam where a future change is likely to land and you want it to land in one place
Skip for trivial or single-call-site code, or interfaces fully dictated by an existing contract.
Process
1. Frame the problem space
Before generating alternatives, write down the constraints, dependencies, the dominant use case, and a rough code sketch of the interface. Use the project's domain language (see [[domain-modeling]]). Vague framing yields vague designs.
2. Generate 2–3 divergent designs
Each design optimizes one distinct goal — they must genuinely differ, not be three shades of the same idea:
| Lens | Optimizes for |
|---|---|
| Minimize entry points | Fewest interfaces, maximum leverage per surface — a deep module |
| Maximize flexibility | Reuse across the widest set of use cases |
| Optimize the common case | Simplest path for the dominant workflow |
| Isolate seams | Cross-boundary dependencies behind ports & adapters |
Orchestration: if the Agent/Task tool is available, fan out one agent per design in parallel, each with the same framing and a different lens. No agent teams or debate are needed — the designs are independent. If agents are unavailable, produce the designs sequentially yourself. Each brief returns the interface sketch plus its trade-offs.
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.
- 4d ago First seen · 78 lines · 44 tokens per session scan A fbac7454b4ce
design-it-twice is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 921 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…