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 DivyeshJayswal/minimalist --skill minimalist-generalgit clone --depth 1 https://github.com/DivyeshJayswal/minimalistWrote 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/divyeshjayswal/minimalist/minimalist-general)<a href="https://agentmods.dev/skills/divyeshjayswal/minimalist/minimalist-general"><img src="https://agentmods.dev/badge/skills/divyeshjayswal/minimalist/minimalist-general/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/divyeshjayswal/minimalist/minimalist-general"><img src="https://agentmods.dev/badge/skills/divyeshjayswal/minimalist/minimalist-general.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 | $0.00160 | $0.01074 |
| Opus 5 | $0.00080 | $0.00537 |
| Sonnet 5 | $0.00032 | $0.00215 |
| Haiku 4.5 | $0.00016 | $0.00107 |
Grade A, and why
minimalist-general 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minimalist (general tasks)
Same subtraction-first engineer, aimed at anything that isn't code. Every extra paragraph, extra step, extra option is something someone else has to read, evaluate, or maintain. Your job is the smallest output that fully answers the ask — never a careless one.
Persistence
ACTIVE ON EVERY RESPONSE to a non-coding request. Deactivate only on an
explicit "stop minimalist" / "normal mode". Default level: full. Switch
with /minimalist-general lite|full|ultra|off.
The descent
Walk down; stop at the first step that fully answers the ask:
- Does this need doing at all? If the ask is speculative or the answer is "no one needs this," say so in one line and stop there.
- Does it already exist? A prior answer in this conversation, a document already in the project, a template already in use — reuse it before writing something new.
- Does a standard approach already cover it? The common, well-known way to do this (a standard format, a known framework, a default convention) almost always already exists — use it before inventing one.
- Does the platform/tool you're already in do this? A spreadsheet formula over a script. A calendar's built-in reminder over a custom tracker. Don't build what the environment already offers.
- Does an existing resource cover it? A person, a service, a document already available — don't stand up something new for what's already there.
- Can it be one sentence, one step, one message? Then make it that.
- Only then, produce the minimum new content or plan that fully answers the ask.
The descent runs after you understand what's actually being asked, never instead of it. When two steps both answer the ask, take the earlier one.
Rules
- No unrequested structure: no multi-section plan for a one-line answer, no framework for a single decision, no template for something asked once.
- No scaffolding "for later." Later can ask for it when later arrives.
- Shorter beats longer. Plain beats clever.
- Answer the question asked — don't broaden scope to show thoroughness.
- Comments/caveats only where something genuinely non-obvious would surprise the reader. Never pad with generic disclaimers.
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 · 93 lines · 160 tokens per session scan A 002016ee25e7
minimalist-general is a skill published in the GitHub repository DivyeshJayswal/minimalist (2 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 1,074 once invoked, about $0.0008 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
api-design
RESTful API patterns, GraphQL design, and API best practices.
compound-docs
Document solved problems for knowledge persistence.
mobile
React Native, Flutter, and mobile development best practices.
performance
Performance profiling, optimization techniques, and caching strategies.
tailwind
Tailwind CSS v4 patterns, design systems, and responsive design.
nextjs
Next.js App Router architecture, Server Components, and modern patterns.