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 int2t05/engineering-skills --skill prototypegit clone --depth 1 https://github.com/int2t05/engineering-skillsWrote 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/int2t05/engineering-skills/prototype)<a href="https://agentmods.dev/skills/int2t05/engineering-skills/prototype"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/prototype/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/int2t05/engineering-skills/prototype"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/prototype.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 | $0.00023 | $0.00338 |
| Opus 5.5 | $0.00009 | $0.00135 |
| Sonnet 5.5 | $0.00005 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
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 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.
What it actually says
Prototype
When to use
- Build a bounded disposable experiment to resolve a specific uncertainty.
Not for: implement for production work.
Steps
-
State one uncertainty, observable criterion and effort bound; choose the simplest runnable form.
-
Implement only what exercises it; label simulated behavior and synthetic data.
-
Run and inspect the experiment against its criterion.
-
Report conclusions in conversation or an approved findings path; retain or remove the prototype according to its actual use.
Output: Suggested paths, subject to human audit: docs/design/prototype-findings.md when conclusions need persistence.
Verify
- The experiment was run and narrows its question; simulated behavior is not presented as real integration.
References
- engineering-principles.md — shared decision boundaries, scope and verification.
- design-principles.md — design discipline (hierarchy before decoration, design every state, recognize rather than recall).
- human-audit.md — document consent, readability and human review.
- references/logic.md — single-shareable-HTML logic prototype: pure module, free-play + guided walkthroughs
- references/ui.md — toggleable UI variants: sub-shape A (existing page) vs B (throwaway route), floating switcher
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.
- 10d ago Changed · -30 lines · -70 tokens per session 8b552c03f2b2
- 16d ago Changed · +3 lines 9e404d650afd
- 1mo 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 11d ago), licensed MIT. It adds 23 tokens to every session and 338 once invoked, about $0.0001 per session on Opus 5.5. 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
design-reviewer
Use after AC and before RED for any wave that ships UI. Performs component API audit against installed dist files, produces per-route mockup, defines visual ACs, flags design-system gaps. Output written to .wave/dr.md.
nw-fp-usable-design
Naming conventions, API ergonomics, and usability patterns for functional code.
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
aesthetic-instrument
A committed aesthetic in the sense of skills/committed-aesthetic/SKILL.md: every rule below is checkable, and every value was read out of the source — packages/board/public/index.html and greatcto-site/styles.css — rather than chosen to write this document.
committed-aesthetic
How to write — and how to use — a skill that IS one aesthetic rather than a catalogue of them. A catalogue lets an agent pick, and it picks the modal option; a committed aesthetic makes it execute one thing precisely, against rules you can check. Use when a design keeps coming out competent and forgettable, when…
plan
Analyzes architecture, selects patterns, assesses testability, then decomposes work into ordered TDD tasks with exact verification commands and explicit acceptance mapping. Works from an approved spec (zuvo:brainstorm output) or directly from a user-provided description.