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 fady-ramzy91/community-ai-skills --skill clean-classesgit clone --depth 1 https://github.com/fady-ramzy91/community-ai-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/skills/fady-ramzy91/community-ai-skills/clean-classes)<a href="https://agentmods.dev/skills/fady-ramzy91/community-ai-skills/clean-classes"><img src="https://agentmods.dev/badge/skills/fady-ramzy91/community-ai-skills/clean-classes/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/fady-ramzy91/community-ai-skills/clean-classes"><img src="https://agentmods.dev/badge/skills/fady-ramzy91/community-ai-skills/clean-classes.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 | $0.00109 | $0.01391 |
| Opus 5 | $0.00055 | $0.00696 |
| Sonnet 5 | $0.00022 | $0.00278 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
clean-classes 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 10d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Classes (Clean Code, Ch. 10)
Run this skill on one target type at a time. Language may be Swift, Kotlin, Java, TypeScript, or anything else — the procedure does not change.
If the user did not name a type, ask which class (or file) to run on. Do not scan the whole repo unless they asked for that.
Copy and track:
Clean Class Run:
- [ ] Target type identified
- [ ] Inventory (methods, fields, concretes, switches)
- [ ] Naming test (25 words, no and/or/but)
- [ ] Reasons to change listed
- [ ] Cohesion clusters mapped
- [ ] Open/Closed (switch-on-kind) checked
- [ ] DIP (concretes in policy) checked
- [ ] Split executed if more than one responsibility
- [ ] Each new type re-audited (must pass)
- [ ] Report delivered
Rules that decide a split
A type must be split if any of these fail:
- Naming test — cannot describe it in ~25 words without "and," "or," or "but."
- SRP — more than one reason to change (product, network, cache, format, analytics, validation, persistence are different reasons).
- Cohesion — methods form clusters that barely share fields.
- Open/Closed — a
switch/when/ if-else onkind/type/ enum grows for every new variant. - DIP — high-level policy names concretes (
URLSession,Retrofit,UserDefaults, Room, shared prefs) or hidden singletons.
Vague names (Manager, Helper, Processor, Super…, Util) are a smell, not proof — still run the tests above.
A type must not dump leftover jobs into one "helper." Orchestrators (ViewModel, use case) delegate; they do not own networking, cache, formatting, or analytics.
Do not expose private methods just to test them. Extract a type and test that.
Procedure
1. Inventory
From the target type, list:
- Public API (methods the callers use)
- Private helpers
- Instance/static fields
- Concrete types it constructs or calls (
URLSession.shared,Retrofit, disk, analytics SDK) switch/when/ if-else on kind
2. Naming test
What ships with it
3 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.
- 10d ago First seen · 150 lines · 109 tokens per session scan A cf6d1144f0f8
clean-classes is a skill published in the GitHub repository fady-ramzy91/community-ai-skills (1 stars, last pushed 16d ago), licensed MIT. It adds 109 tokens to every session and 1,391 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…