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/yoeld-wix/quiet-bash/minimal-docsnpx skills add yoeld-wix/quiet-bash --skill minimal-docsgit clone --depth 1 https://github.com/yoeld-wix/quiet-bashWrote 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/yoeld-wix/quiet-bash/minimal-docs)<a href="https://agentmods.dev/skills/yoeld-wix/quiet-bash/minimal-docs"><img src="https://agentmods.dev/badge/skills/yoeld-wix/quiet-bash/minimal-docs.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 5.1 | $0.00100 | $0.00575 |
| Opus 5 | $0.00050 | $0.00287 |
| Sonnet 5 | $0.00020 | $0.00115 |
| Haiku 4.5 | $0.00010 | $0.00057 |
Grade A, and why
minimal-docs 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 6d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write the Fewest Rows That Fully Document It
quiet-bash's hooks cut the input you re-send every turn. This is the output-side, prose edition: the markdown the model generates is billed ~3–5× input, produced one token at a time, and re-read on every later turn. Fewer rows means a cheaper, faster turn — and less for the reader to wade through and you to maintain.
The target is the fewest rows that fully document what the reader needs. Short is not the goal by itself: a terse doc that omits a required step, or buries the one fact the reader came for, costs far more than it saves.
The no-regression floor (never shrink these)
Cutting rows must never cut substance. Always keep:
- install / setup / run steps,
- required warnings and security or accuracy caveats,
- copy-pasteable commands and config (exact, not paraphrased),
- anything the user explicitly asked to document.
Concise means cutting filler, not detail. When brevity and clarity conflict, clarity wins — a clear sentence beats a cryptic fragment.
Understand before you shrink
Know the doc's audience and purpose first. Terseness in the wrong place loses readers; trimming a section you haven't understood is how the missing step ships.
Reach for the least first
Go down this list until the doc is complete:
- Don't write sections nobody asked for — no speculative FAQs, no restating the obvious, no closing summary that repeats the intro.
- Link to an existing doc instead of duplicating its content.
- One good example beats three near-identical ones.
- Table or list instead of a paragraph when the content is structured.
- Cut hedging, filler, and narration of obvious steps.
- When two phrasings carry the same information, choose the shorter one.
Inspired by the open-source ponytail project (MIT), which delivers this idea
as a dedicated cross-agent tool. This skill is quiet-bash's lightweight, in-repo
take — the prose sibling of minimal-change (which trims generated code).
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.
- 6d ago First seen · 46 lines · 100 tokens per session scan A ffcf5be8fd0f
minimal-docs is a skill published in the GitHub repository yoeld-wix/quiet-bash (5 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 575 once invoked, about $0.0005 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
lithium-kb
Generates, maintains, and visualizes a structured Markdown knowledge base (.lithium-kb/{architecture,debug,tasks,features}) with an interactive Neural Network graph, auto-watch mode, custom agent directives (.agentrules), and MCP server integration for Pi, Claude, Codex, Cursor, and other coding agents. Triggers…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.