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 shinpr/nautilus --skill recipe-prototype-promptgit clone --depth 1 https://github.com/shinpr/nautilusWrote 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/shinpr/nautilus/recipe-prototype-prompt)<a href="https://agentmods.dev/skills/shinpr/nautilus/recipe-prototype-prompt"><img src="https://agentmods.dev/badge/skills/shinpr/nautilus/recipe-prototype-prompt/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/shinpr/nautilus/recipe-prototype-prompt"><img src="https://agentmods.dev/badge/skills/shinpr/nautilus/recipe-prototype-prompt.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 | $0.00044 | $0.00457 |
| Opus 5 | $0.00022 | $0.00229 |
| Sonnet 5 | $0.00009 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
recipe-prototype-prompt 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype Prompt Export
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
prototype-guide— prototype quality and external prompt construction - [LOAD IF NOT ACTIVE]
design-perspective— product design decisions, persona context, and accessibility
Input
Use the hypothesis path and target platform supplied with the explicit skill invocation. If either cannot be inferred unambiguously, ask for the missing value.
Process
- Read the target hypothesis and extract the decision under test, scenario, and observable success/failure criteria.
- Read the loaded
prototype-guideskill'sreferences/prototype-quality.mdand acquire only product/design sources that can change the generated prototype or its evaluation. - Read the loaded
prototype-guideskill'sreferences/prototype-prompt-guide.mdand the selected platform template when one exists. - Materialize the decision-relevant product, design, component, and data context in the prompt unless the target generator has verified repository access.
- Write the machine-executable prompt to
docs/discovery/prototypes/hypo-{id}-{platform}-prompt.md.
Output Contract
Return the prompt path, target platform, decision under test, and source paths used. Source paths provide traceability and become generator instructions only when the target has verified access to them. The prompt contains only instructions consumed by the external generator; add a separate guide only when a named human consumer needs information that would degrade the executable prompt.
Scope Boundary
This recipe does not generate the HTML prototype, execute validation, or update the hypothesis record. Use recipe-validate for the context-separated generation and validation lifecycle.
Completion
The workflow is complete when docs/discovery/prototypes/hypo-{id}-{platform}-prompt.md exists at the reported path and its content carries the applicable prototype quality criteria and decision-relevant product context.
What ships with it
1 file 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.
- 4d ago Changed · +2 lines a99c205e3990
- 9d ago First seen · 37 lines · 44 tokens per session scan A 870ecb3fa43d
recipe-prototype-prompt is a skill published in the GitHub repository shinpr/nautilus (4 stars, last pushed 8d ago), licensed MIT. It adds 44 tokens to every session and 457 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 2026-08-31.
Other skills, from other repositories
productspec
Use when implementing, reviewing, planning, or changing work governed by a Product Spec. Treat .product-spec.md files as the product contract for the work.
productspec-authoring
Writes, validates, and converts ProductSpec files (.product-spec.md), the Markdown format for recording product intent before implementation. Use when authoring a new Product Spec, converting an existing PRD or feature doc into one, validating spec files locally or in CI, or recording how a spec's intent changed over…
product-principles
Defines 4 Risks confidence thresholds, OST hierarchy levels, Knowledge Pyramid tiers, and state design requirements. Use when evaluating user stories, setting confidence scores, referencing OST levels, scoping MVP, or determining validation sufficiency.
recipe-define
Orchestrate PRD creation from validated hypotheses — standard PRD output with 4 Risks confidence and hypothesis traceability.
recipe-validate
Orchestrate hypothesis validation through type-appropriate methods — prototypes, code analysis, market research, and expert review.
hypothesis-discipline
Manages hypothesis lifecycle, enforces validation criteria, time budgets, and confidence scoring rules. Use when creating hypotheses, updating confidence scores, setting validation criteria, handling timeouts, or recording validation results.