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/clean-codenpx skills add fellipeutaka/leon --skill clean-codegit 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 | $0.00067 | $0.02033 |
| Opus 5 | $0.00034 | $0.01017 |
| Sonnet 5 | $0.00013 | $0.00407 |
| Haiku 4.5 | $0.00007 | $0.00203 |
Grade A, and why
clean-code 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code
Principles for transforming "code that works" into "code that is clean" — code that can be read, understood, and enhanced by any developer.
"Code is clean if it can be understood easily — by everyone on the team." — Dave Thomas
When to Apply
Reference these guidelines when:
- Writing new code and choosing names, function signatures, structure
- Reviewing pull requests for readability and maintainability
- Refactoring legacy code or reducing complexity
- Identifying and fixing code smells
- Improving team code standards
Rule Categories
| Priority | Category | Impact |
|---|---|---|
| 1 | Naming | HIGH — affects every line of code |
| 2 | Functions | HIGH — core unit of abstraction |
| 3 | Code Smells | HIGH — early detection prevents rot |
| 4 | Formatting | MEDIUM — readability at a glance |
| 5 | Error Handling | MEDIUM — robustness and clarity |
| 6 | Comments | MEDIUM — most are avoidable |
| 7 | Object Calisthenics | ASPIRATIONAL — exercises for better OO design |
1. Naming
Good names are the single most impactful thing you can do for readability.
Priority order:
- Consistency — same concept = same name everywhere
- Intent-revealing — name says what it does, not how
- Specific — avoid vague names like
data,info,manager,handler,utils - Searchable — unique enough to grep
- Brief — short but not cryptic
// Bad
const d = new Date();
const arr = users.filter((u) => u.a);
function process(data: any) {}
// Good
const createdAt = new Date();
const activeUsers = users.filter((user) => user.isActive);
function validatePayment(payment: Payment) {}
Conventions:
- Classes/types: nouns (
Customer,OrderRepository). AvoidManager,Data,Info. - Methods/functions: verbs (
createOrder,validateEmail,isEligible) - Booleans: question form (
isActive,hasPermission,canWithdraw) - Collections: plural nouns (
users,orderItems)
What ships with it
4 files 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 · 233 lines · 67 tokens per session scan A e6c795dd3c27
clean-code is a skill published in the GitHub repository fellipeutaka/leon (5 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 2,033 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.
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…