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 safitudo/leap-skill --skill leapgit clone --depth 1 https://github.com/safitudo/leap-skillWrote 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/safitudo/leap-skill/leap)<a href="https://agentmods.dev/skills/safitudo/leap-skill/leap"><img src="https://agentmods.dev/badge/skills/safitudo/leap-skill/leap/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/safitudo/leap-skill/leap"><img src="https://agentmods.dev/badge/skills/safitudo/leap-skill/leap.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 | $0.00069 | $0.03443 |
| Opus 5 | $0.00034 | $0.01722 |
| Sonnet 5 | $0.00014 | $0.00689 |
| Haiku 4.5 | $0.00007 | $0.00344 |
Grade A, and why
leap 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 9d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LEAP — LLM Engineered Application Pattern
You are operating in a LEAP project. Code is not the product — prompts, schemas, and tests are. You are the compiler.
Philosophy
- Prompts describe intent. They are declarative, not imperative.
- Schemas define contracts between parts. They ARE the architecture.
- Tests specify correctness. They are human-authored guardrails. They are the most valuable artifact.
- Code is a commodity. It is generated, not written. It is disposable. It lives in
src/and is gitignored.
The guardrails hierarchy (most to least valuable):
- Tests — the specification of correctness
- Schemas — the architecture
- Prompts — the intent (if you lose a prompt but keep tests + schemas, any new prompt that passes is equally valid)
How to operate
When you encounter a LEAP project (has master.md at root):
- Read
master.md— it contains the app description and generation instructions - Read all schemas in
schemas/— these are the contracts - Read all parts — each
parts/*/master.mdhas a prompt, eachparts/*/schema.tshas a contract - Generate code into
src/— satisfy every contract - Install dependencies — run
npm install(or equivalent) - Run tests — they must all pass
- Fix until green — if tests fail, fix the generated code and re-run
- Run the app — if
master.mdhas a "Running the app" section, execute it
Rules
- Do not ask questions. Do not summarize. Do not confirm. Just build.
- Do not modify anything outside
src/. Prompts, schemas, and tests are human-authored. You only generate code. src/must be self-contained. No imports from outsidesrc/. Copy type definitions inline if needed.- Generated code must work without a build step unless the project explicitly requires one.
- Tests are the authority. If a test contradicts a prompt, the test wins.
- Start immediately after reading all schemas and parts.
DO NOT CHEAT
The whole point of LEAP is that AI generates code from prompts, schemas, and tests. If you copy code from somewhere else, the experiment is invalid and the project's value is destroyed.
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.
- 9d ago First seen · 269 lines · 69 tokens per session scan A 223513b4a5b7
leap is a skill published in the GitHub repository safitudo/leap-skill (6 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 3,443 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…