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/orlando-japan/claude-code-setting/simplicity-firstnpx skills add orlando-japan/claude-code-setting --skill simplicity-firstgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/simplicity-first)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/simplicity-first"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/simplicity-first.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00491 |
| Opus 5 | $0.00016 | $0.00246 |
| Sonnet 5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
simplicity-first 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 5d 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.
What it actually says
Simplicity first
The default LLM failure mode is overbuilding. This skill is the counterweight.
Apply when
- You're about to add a helper, interface, or base class.
- You're adding a config flag "in case."
- You're handling an error that can't actually occur.
- You're refactoring something unrelated because you're "already in the file."
The five checks
Before writing a piece of code, ask:
- Does this line of code exist to satisfy the actual request? If not, delete it.
- Is this abstraction pulling its weight today? One caller = inline it. Three callers that look similar = probably extract. Two = think about it.
- Am I handling a case that can happen? If the type system, the caller, or the framework already guarantees it, drop the handler.
- Am I adding a knob for a future need I can't name? Remove the knob. Add it when the second real need shows up.
- Would deleting this make the code wrong? If no, it's dead weight.
Concrete targets to cut
- Dead branches.
if (!x) return;whenxis guaranteed non-null by the type. - Trivial wrappers.
function getName(u) { return u.name; }— just useu.name. - Speculative configs.
retryCount: options.retryCount ?? 3when nothing passesretryCount. - Empty tests. A test that calls the function and asserts nothing useful.
- Boilerplate comments.
// Initialize the variableaboveconst x = 0.
Counter-pressure
The principle isn't "never abstract" — it's "abstract on demand." When you extract, it should be because concrete code duplication was hurting, not because abstraction might pay off later.
Done check
Before committing: re-read the diff and remove anything that, if deleted, would still satisfy the task. If you can't remove anything, you've probably gone too far the other way.
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.
- 5d ago First seen · 46 lines · 33 tokens per session scan A 809a981a0901
simplicity-first is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 491 once invoked, about $0.0002 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
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
minimalist-ui
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
react-grab
Use when the user wants a hands-free loop where grabbing UI elements in the browser with React Grab feeds tasks to the agent automatically, with no copy-paste or manual handoff. Triggers: "watch react grab", "monitor my grabs", "auto-process react grab", "watch my clipboard for grabs". Not for a one-off paste of a…
rowan
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve…