minimalist-gain

minimalist-gain is a skill for Claude Code from DivyeshJayswal/minimalist. It costs 48 tokens per session (241 once invoked), scanned A, original, MIT.

A report of the minimalist changes recorded in the current project or session, such as rejected scope or avoided lines. It reads the project's saved rejection ledger rather than relying on memory.

In plain words
What is it for?
Use it when you want a savings report for minimalist reviews or changes. It can also compare drafted alternatives when both versions were genuinely counted.
Why use it?
It provides an evidence-based account of what was actually left out, while distinguishing estimates from measured results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the minimalist plugin — 6 skills, 2 hooks shipped together

Good fit Use it when you want a savings report for minimalist reviews or changes. It can also compare drafted alternatives when both versions were genuinely counted.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/divyeshjayswal/minimalist/minimalist-gain
Install

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.

Any agent
npx skills add DivyeshJayswal/minimalist --skill minimalist-gain
Clone the repo
git clone --depth 1 https://github.com/DivyeshJayswal/minimalist

Made for: Claude Code.

Or install minimalist, the plugin that ships this one along with the rest of its 6 skills, 2 hooks.

Wrote 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.

agentmods badge for minimalist-gain

README.md
[![agentmods](https://agentmods.dev/badge/skills/divyeshjayswal/minimalist/minimalist-gain/github.svg)](https://agentmods.dev/skills/divyeshjayswal/minimalist/minimalist-gain)
Your own site
<a href="https://agentmods.dev/skills/divyeshjayswal/minimalist/minimalist-gain"><img src="https://agentmods.dev/badge/skills/divyeshjayswal/minimalist/minimalist-gain/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.

agentmods 80×15 button for minimalist-gain

Your own site · 80×15
<a href="https://agentmods.dev/skills/divyeshjayswal/minimalist/minimalist-gain"><img src="https://agentmods.dev/badge/skills/divyeshjayswal/minimalist/minimalist-gain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00241
Opus 5 $0.00024 $0.00120
Sonnet 5 $0.00010 $0.00048
Haiku 4.5 $0.00005 $0.00024

Measured 10d ago against content hash 86b128099c40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

minimalist-gain 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.

.openclaw/skills/minimalist-gain/SKILL.md · 25 lines

What it actually says

Minimalist Gain

Run node scripts/log-rejection.js --report from the repo root and report its output verbatim (or summarized, not altered) — this is the persisted ledger of every rejected-scope line logged across sessions, not just this one. Its "lines avoided" total, when present, is the agent's estimate at logging time, not a measurement — keep that label attached, don't restate it as a hard number. If the script is missing or the ledger is empty, say so plainly instead of falling back to memory.

Also report, only if actually countable this session:

  • LOC of the shipped diff vs. the LOC of the approach you rejected, when both were actually drafted.

Never extrapolate to cost or percentages you did not compute. Point to benchmarks/ for reproducible aggregate numbers.

Changes

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.

  1. 10d ago First seen · 25 lines · 48 tokens per session scan A 86b128099c40

Subscribe to this mod's changes

minimalist-gain is a skill published in the GitHub repository DivyeshJayswal/minimalist (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 241 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.