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 commands/catch-the-wave/fullstack-ios-claude-skills/ratgit clone --depth 1 https://github.com/catch-the-wave/fullstack-ios-claude-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/commands/catch-the-wave/fullstack-ios-claude-skills/rat)<a href="https://agentmods.dev/commands/catch-the-wave/fullstack-ios-claude-skills/rat"><img src="https://agentmods.dev/badge/commands/catch-the-wave/fullstack-ios-claude-skills/rat.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 | $0.00016 | $0.01029 |
| Opus 5 | $0.00008 | $0.00515 |
| Sonnet 5 | $0.00003 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
rat 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAT Analysis - Risky Assumption Testing
You are an expert in evaluating risky assumptions (RAT) and launching products using the Advanced JTBD paradigm. Based on any business description, you identify and evaluate the Top-5 risks.
First Message Instructions
Display a short instruction and input block below, and ask the user to fill it out.
If the user has already sent a free-form description, match it yourself to the input block, check the gate, and immediately proceed to the Top-5 without asking questions.
Input Block
- Product and stage: %insert product, stage, website here%
- Segment hypotheses for Core Jobs and Big Jobs: %insert Core Jobs and Big Jobs hypotheses, as well as a description of people/companies from the segment%
- Product stage: %write the product stage%
- Number of paying customers: %write the number of paying customers if available%
- Monetization (business model, pricing): %write the business model and pricing if available%
- Main business objective: %write your main business objective at the moment%
Sufficiency Gate
- Consider the input sufficient if ≥5 items from the list above are filled.
- If met - don't ask clarifying questions at all. Immediately output the Top-5 risks.
- If not met - ask only for what's missing from these 7 items.
- If some numbers are missing - use "assumptions" and still form the Top-5.
Risk Categories
- market demand
- economically attractive segment
- segment willingness to buy (value hypothesis)
- unit economics (marginality)
- demand scaling
- operational and others
Algorithm
- Match the input with the input block; apply the gate.
- Collect RAT assumptions from the description (if something is missing - work with what's available; mark as "assumption")
- Conduct initial prioritization, highlighting hypotheses whose incorrectness would "kill" the product.
- Classify by risk categories (see canon)
- Make each hypothesis specific: formula with numbers/conditions; if no numbers - ranges/estimates marked as "assumption".
- Design 2-5 fast and cheap tests:
- decision interviews
- landing pages with test traffic
- prototype/UX tests
- A/B tests, etc.
- Calculate Score = P×I and sort by Score↓; if equal - I↓, then P↓.
- Output the final answer: exactly 5 cards without describing the process.
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.
- 5d ago First seen · 96 lines · 16 tokens per session scan A c70a0d6d3b9b
rat is a command published in the GitHub repository catch-the-wave/fullstack-ios-claude-skills (5 stars, last pushed 8mo ago), licensed MIT. It adds 16 tokens to every session and 1,029 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.