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/5uck1ess/devkit/clean-codenpx skills add 5uck1ess/devkit --skill clean-codegit clone --depth 1 https://github.com/5uck1ess/devkitWhat 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 | $0.00023 | $0.00506 |
| Opus 5 | $0.00012 | $0.00253 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code
Meaningful Names
- Names should reveal intent.
getUserByIdnotgetData.isExpirednotcheck. - Don't abbreviate unless the abbreviation is universally understood (
url,id,config). - Booleans read as questions:
isReady,hasPermission,shouldRetry. - Functions read as actions:
calculateTotal,validateInput,sendNotification.
Small Functions
A function should do one thing. If you're describing what a function does and use the word "and," it does too much.
Aim for 5-15 lines. Not a hard rule, but long functions almost always contain extractable sub-functions.
Single Responsibility
Every module/class/function should have one reason to change. If a module handles both parsing and validation, a change to parsing rules forces you to touch validation code (and vice versa).
Ask: "If requirement X changes, how many files do I touch?" If the answer is many, responsibilities are entangled.
The Stepdown Rule
Organize code so readers encounter high-level logic first, details later. A file should read like a newspaper article — headline, summary, then details.
// Good: high-level flow is immediately clear
function processOrder(order) {
validate(order);
const total = calculateTotal(order.items);
return submitPayment(order.customer, total);
}
// Supporting functions follow below
function validate(order) { /* ... */ }
function calculateTotal(items) { /* ... */ }
function submitPayment(customer, total) { /* ... */ }
Public/exported functions at the top. Private/helper functions below.
Flat Nesting
Deeply nested code is hard to follow. Prefer early returns, guard clauses, and extraction.
// Bad: nested
function process(input) {
if (input) {
if (input.isValid) {
if (!input.isProcessed) {
return doWork(input);
}
}
}
return null;
}
// Good: flat
function process(input) {
if (!input) return null;
if (!input.isValid) return null;
if (input.isProcessed) return null;
return doWork(input);
}
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 · 74 lines · 23 tokens per session scan A 22aa7f14fef7
clean-code is a skill published in the GitHub repository 5uck1ess/devkit (5 stars, last pushed 13d ago), licensed MIT. It adds 23 tokens to every session and 506 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
dynamic-workflows
Ultracode / Max-Parallel mode — dynamic workflows fan work out across tens–hundreds of adversarially-verified parallel subagents for large, decomposable jobs (codebase-wide audits, big migrations, cross-checked research). Opt-in; higher token spend.
cost-efficiency
Smart Routing — the DEFAULT CCGodMode routing policy. Risk-based, minimal-agent paths that preserve required safety gates for the changed scope.
agent-teams
Experimental Agent Teams orchestration — run CCGodMode agents as parallel teammates with SharedTaskList coordination (requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1).
quality-gates
Parallel quality gate orchestration — @validator and @tester run simultaneously after @builder, with mandatory decision matrix for pass/fail routing.
sprint-planning
Plan-first orchestration (ADR-004): comprehensive PLAN.md, sprint files with write-scope ownership, preflight checks, serialized integration, and the release sprint. Use for any non-trivial or multi-part request BEFORE dispatching agents.
workflows
CCGodMode Full-Gates workflow definitions — used for high-risk work and when Smart Routing escalates. Default routing is Smart Routing (skills/cost-efficiency/).