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 skills/fellipeutaka/leon/implementnpx skills add fellipeutaka/leon --skill implementgit clone --depth 1 https://github.com/fellipeutaka/leonWhat 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 | $0.00016 | $0.01127 |
| Opus 5 | $0.00008 | $0.00563 |
| Sonnet 5 | $0.00003 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
implement 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement the work described by the user in the spec or tickets.
Use /tdd where possible, at pre-agreed seams.
Run typechecking regularly, single test files regularly, and the full test suite once at the end.
Once done, use /code-review to review the work.
Delivery mode
Choose the delivery mode from the user's instruction, the repository's AGENTS.md, or the current branch state. Do not infer stacked or integration delivery merely because a feature has multiple tickets.
Standalone delivery
Use standalone delivery by default when no stack has been requested:
- Commit the work to a new branch named
feat/implement-<short-description-of-work>. - Create a pull request against the appropriate trunk or parent branch, closing the ticket or spec.
Stacked delivery
Use stacked delivery when the user requests it or the repository explicitly enables it for the current flow. The /gh-stack skill is the operational reference for stack commands.
Before writing code:
- Read the full ticket and verify that its real blockers are complete or that the requested parent branch already contains them.
- Confirm the worktree is clean.
- Run
gh stack view --jsonto inspect the current stack. If it reports that the branch is not in a stack, initialize or continue with standalone delivery as appropriate. If the existing implementation branch already has a PR, adopt it withgh stack init <existing-branch>rather than recreating the branch or PR. - Plan the layer against the immediate parent. A ticket dependency graph can contain forks and joins;
gh-stackis strictly linear. Do not append a sibling or join ticket to a stack unless serializing that work is an intentional decision.
Create and navigate branches with gh stack:
- For the first layer, use
gh stack init feat/implement-<short-description-of-work>. - For each subsequent layer, use
gh stack add feat/implement-<short-description-of-work>while checked out on the stack top. - Use standard
git addandgit commitfor deliberate staging; do not usegit switch -cfor a stacked layer.
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.
- yesterday First seen · 84 lines · 16 tokens per session scan A 693294c53aa7
implement is a skill published in the GitHub repository fellipeutaka/leon (5 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 1,127 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…