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 luabagg/agent-skills --skill natural-copy-editinggit clone --depth 1 https://github.com/luabagg/agent-skillsWrote 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/luabagg/agent-skills/natural-copy-editing)<a href="https://agentmods.dev/skills/luabagg/agent-skills/natural-copy-editing"><img src="https://agentmods.dev/badge/skills/luabagg/agent-skills/natural-copy-editing/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/luabagg/agent-skills/natural-copy-editing"><img src="https://agentmods.dev/badge/skills/luabagg/agent-skills/natural-copy-editing.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 | $0.00045 | $0.00536 |
| Opus 5 | $0.00023 | $0.00268 |
| Sonnet 5 | $0.00009 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
natural-copy-editing 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 3d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Natural Copy Editing
Core Rule
Assume the user wants clean copy-paste output. Give the revised text, not commentary about the revision, unless they ask for explanation or options.
Defaults
- Preserve the user's original tone unless they request a different one.
- If the text is casual, keep it casual.
- If the text is professional, make it clear without sounding corporate or robotic.
- Prefer natural, direct writing. Remove all mannered prose.
- If the text sounds machine-written, apply the
humanizerpattern list. Keep this skill's output format: final text only, no critique. - Avoid corporate filler like "I hope this message finds you well" and "kindly" unless it matches the user's tone.
- Use straight apostrophes only: I'm, don't, it's, you're.
- Do not use em dashes. Use a hyphen "-" when a dash is needed.
Output Format
- For direct rewrite, translation, and correction requests, output only the revised text.
- Do not add labels like "Improved version:" unless requested.
- Do not provide multiple options unless the user asks for options.
- Do not wrap the answer in quotation marks or code fences unless requested.
- Do not format as Markdown unless the user explicitly asks for Markdown, or says it is for a Markdown-like platform such as a GitHub pull request, Linear ticket, Notion, Obsidian, README, issue, or documentation.
- Keep formatting minimal. Avoid excessive headings, bold text, bullets, tables, or decorative structure unless requested.
Translation And English Corrections
- For translations, preserve the intended tone and context rather than translating word-for-word.
- For translations, output only the translated text unless the user asks for notes.
- For English corrections, fix grammar, clarity, flow, and structure while preserving the user's voice.
- Preserve meaning, urgency, hedging, politeness, and constraints like "no rush" or "today".
Common Mistakes
| Mistake | Fix |
|---|---|
| Adding "Here's a cleaner version" | Output only the revised text |
| Making casual text corporate | Keep it natural and close to the user's voice |
| Offering three versions unasked | Give one strong version |
| Explaining each change | Only explain if asked |
| Using Markdown by default | Use plain text unless requested |
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.
- 3d ago Changed · +11 tokens per session dac153c768db
- 6d ago Changed a1b4c58303cc
- 10d ago First seen · 48 lines · 34 tokens per session scan A f5c7bf2e45ba
natural-copy-editing is a skill published in the GitHub repository luabagg/agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 536 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
harness
Connect this Bankr account to the user's Harness account (tryharness.ai) and manage everything Harness-side from here. Pair with a signed wallet proof, then inspect the Harness trading wallet and portfolio, fund it on the user's request, request withdrawals back to this wallet, buy Harness credits with $HARNESS over…
web-ui-motion
Build polished front-end UI together with a signature motion effect in a single self-contained HTML file, combining SVG.js / SVG filters and the Canvas 2D API. Use when the user asks to build a web page, landing page, dashboard, or component that has a special visual effect, animation, particle system, fluid/water…
openspec-propose
Create a complete OpenSpec proposal with design, specs, prototype, and tasks. Use when the user wants a change ready for implementation.
prototype-workflow
Generate and lifecycle-manage HTML prototypes for UI exploration and OpenSpec changes. Use when creating, validating, completing, or archiving a UI prototype.
html-output
Produce rich, self-contained, single-file HTML as the default output format instead of Markdown — for specs, plans, code reviews, PR write-ups, reports, explainers, design explorations, slide decks, SVG diagrams, and small interactive editors with copy-as-prompt/JSON export. USE WHEN the user asks to "make an HTML…
harness-engineering-guide
Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full…