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/uwuclxdy/agenticat/clean-codenpx skills add uwuclxdy/agenticat --skill clean-codegit clone --depth 1 https://github.com/uwuclxdy/agenticatWhat 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 | $0.00022 | $0.04604 |
| Opus 5 | $0.00011 | $0.02302 |
| Sonnet 5 | $0.00004 | $0.00921 |
| Haiku 4.5 | $0.00002 | $0.00460 |
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 2d 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code Principles
Use these when you write, review, or refactor code.
Treat these as directional principles. Where a repo's established precedent or a language's own idioms conflict with a rule here, follow the local convention and match the surrounding code.
1. Naming & Readability
1.1 Avoid Disinformation
Never use variable names that create false expectations, contain misleading technical terms, or use visually confusing characters.
Do:
- Use names that honestly reflect the data structure (
accountsMap,accountsGroup). - Use distinct names for classes/variables so autocomplete doesn't trick you.
Don't:
- Name a map
accountListjust because it holds several items; to a programmer "list" means an indexed structure. - Create names that vary in tiny ways (e.g.,
ABCManagerForEfficientProcessingOfUsersvs...PersistingOfUsers). - Use characters that look identical (lowercase
lvs1, uppercaseOvs0).- Bad:
int a = l; if (O == l) a = O1; else l = O1;
- Bad:
1.2 Make Meaningful Distinctions
If two things have different names, they must do different things. Avoid meaningless noise words and number series.
Do:
- Reveal the actual role of variables (e.g.,
array,condition,transformation). - Use specific, role-based names for classes (e.g.,
OrderValidator,OrderRepository,OrderCalculator).
Don't:
- Add meaningless noise suffixes when you can't think of a better name (e.g.,
OrderManager,OrderHandler,OrderController,OrderProcessorall existing side by side).
1.3 Use Searchable, Pronounceable Names
Names should read as natural words and match the size of their scope, so they can be spoken aloud and found by search. Avoid cryptic abbreviations, single letters outside tiny scopes, and raw magic numbers.
Do:
- Use real words that describe intent.
- Good:
let generationTimestamp = new Date();
- Good:
- Use single letters (
i,j) only in tiny scopes, like a shortforloop.
Don't:
- Mash abbreviations into cryptic strings.
- Use single letters in larger scopes (searching for
ereturns thousands of useless hits). - Use an abbreviation that reads fine but decodes several ways: in
const tx = t[i], istxtime, tax, text, or transaction? A pronounceable, searchable name can still force the reader to keep a lookup table in their head.
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.
- 2d ago First seen · 361 lines · 22 tokens per session scan A 5104f839cf22
clean-code is a skill published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 4,604 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
meta-harness
Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto…
meta-harness-proteus
Run one iteration of proteus memory-summary evolution. Called by metaharness.py.
gbg
Convert any plan, PRD, feature idea, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, refactors, and hardening alike. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt (Codex/etc.), a…
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…