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/int2t05/engineering-skills/prototypenpx skills add int2t05/engineering-skills --skill prototypegit clone --depth 1 https://github.com/int2t05/engineering-skillsWhat 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 | $0.00093 | $0.00841 |
| Opus 5 | $0.00046 | $0.00420 |
| Sonnet 5 | $0.00019 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
prototype 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
A prototype is throwaway code that answers a question. The question decides the shape.
When to use
- "Does this logic / state model feel right?" → logic prototype
- "What should this look like?" → UI prototype
- Sanity-check a state machine or data model before committing; explore UI directions before picking one
- Triggers on "prototype", "throwaway", "mockup", "compare layouts", "validate the interaction", "sketch out", "try this quickly", "build a demo", "原型", "试做", "试这个方案", "搭个快速 demo"
Not for: production UI implementation (use frontend-design); production code (use implement).
Steps
1. Pick a branch
The two branches produce very different artifacts; getting this wrong wastes the whole prototype.
- Logic / state model → load
references/logic.md. Single shareable HTML file with free-play buttons and tabbed guided walkthroughs a non-developer can drive. - What it looks like → load
references/ui.md. Several radically different UI variations on one route, switchable via?variant=and a floating bar.
If the question is ambiguous and the user isn't reachable, default to whichever branch matches the surrounding code (backend module → logic; page/component → UI) and state the assumption up top.
2. Build it throwaway from day one
- Locate it close to where it will be used, but name it so a reader sees it's a prototype
- Trivial to run: one command in the task runner, or a single HTML file double-clicked
- No persistence by default — state in memory; no tests, no abstractions, no polish
- Surface the full relevant state after every action (logic) or variant switch (UI)
3. Capture the answer when done
Fold validated decisions into the real code. Capture the prototype itself as a primary source: commit to a throwaway branch (out of main), leave a context pointer on the implementation issue, and record the verdict + question settled. Main keeps only the validated decision.
Output: docs/design/prototype-findings.md — the question tested, the verdict, and the validated
decision. The prototype code itself stays on a throwaway branch; only the finding is promoted to main
as a durable record.
What ships with it
3 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.
- 2d ago First seen · 64 lines · 93 tokens per session scan A e5929c80f9d1
prototype is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 14d ago), licensed MIT. It adds 93 tokens to every session and 841 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.