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-definegit 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-define)<a href="https://agentmods.dev/skills/shinpr/nautilus/recipe-define"><img src="https://agentmods.dev/badge/skills/shinpr/nautilus/recipe-define.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 5.1 | $0.00035 | $0.01102 |
| Opus 5 | $0.00017 | $0.00551 |
| Sonnet 5 | $0.00007 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
recipe-define 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context: Transform validated hypotheses into a PRD with 4 Risks confidence scores, hypothesis traceability, and user stories. The PRD follows a standard structure that can be consumed by downstream implementation workflows.
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
prd-standards— PRD structure, user stories, and acceptance criteria - [LOAD IF NOT ACTIVE]
product-principles— 4 Risks, confidence thresholds, and MVP scope
Conditional Skills [LOAD WHEN TRIGGERED]
- WHEN the PRD contains user-facing interaction, Design Context, or accessibility requirements: [LOAD IF NOT ACTIVE]
design-perspective
Delegate the completed draft to doc-reviewer for bias-free quality assessment before asking for final product approval.
Execution Decision Flow
1. Readiness Assessment
Input: Use the path or text supplied with the explicit skill invocation. If no input was supplied and the target cannot be inferred unambiguously, ask for it.
Assess whether hypotheses are "validated enough" for PRD creation:
- Read relevant Opportunity and hypothesis files
- For each hypothesis intended for the PRD:
- Check confidence against the product-principles cost, risk, and reversibility criteria
- Assess cost x risk x reversibility
- Determine: validated enough / needs more validation
- See product-principles skill
references/mvp-definition.mdfor scope determination
Decision:
- All key hypotheses validated enough → Proceed to PRD drafting
- Some hypotheses below threshold → Present to user with options:
- Lower threshold (add risk mitigation like feature flags)
- Validate further (→ recipe-validate)
- Proceed with documented remaining risks
2. PRD Drafting
Use prd-standards skill references/prd-template.md to create the PRD:
- Overview: Link to Opportunity and validated hypotheses
- User Stories: Record material 4 Risks evidence at the smallest scope that changes delivery readiness
- Functional Requirements: Derive from validated hypotheses with testable ACs. Use EARS patterns when they clarify the trigger, state, or condition. Assign stable AC IDs when an implementation, test, or planning consumer references individual ACs; keep criteria unnumbered when no such consumer exists
- Design Context: Include the project design decisions and validation artifacts needed by delivery; link the source instead of copying unrelated sections
- Success Criteria: Tie to Product Outcomes from
docs/product/vision.md - Assumptions (Unvalidated): Explicitly list hypotheses NOT yet validated that the PRD proceeds with
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.
- 3d ago Changed · +2 lines 3b4fc2feb343
- 8d ago First seen · 101 lines · 35 tokens per session scan A 91eda4b1443b
recipe-define is a skill published in the GitHub repository shinpr/nautilus (4 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 1,102 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
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…
expand-tasks
Expand all TaskMaster tasks with deep research before coding begins. Reads tasks.json, launches parallel research agents per task in waves using the research-expander agent. Writes findings back to tasks.json. Part of the prd-taskmaster toolkit. Use after PRD is parsed and before implementation. Invoke with…
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.