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/98ping/chip/writing-voicenpx skills add 98ping/chip --skill writing-voicegit clone --depth 1 https://github.com/98ping/chipWrote 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/98ping/chip/writing-voice)<a href="https://agentmods.dev/skills/98ping/chip/writing-voice"><img src="https://agentmods.dev/badge/skills/98ping/chip/writing-voice.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 | $0.00077 | $0.01403 |
| Opus 5 | $0.00039 | $0.00701 |
| Sonnet 5 | $0.00015 | $0.00281 |
| Haiku 4.5 | $0.00008 | $0.00140 |
Grade A, and why
writing-voice 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Example Writing Voice (fictional, this is a template)
This skill analyzes the made-up author of examples/writing-samples/. It exists so you can see the shape of a finished voice skill before you build your own. Do not draft real work in this voice. To make your own: drop your essays in writing-samples/, copy this file to .claude/skills/writing-voice/SKILL.md, and tell Claude "rebuild this voice skill from my real samples."
0. Hard guardrails (always apply, no exceptions)
These override everything else in this sheet. Every draft must follow them, every time:
- NO EM DASHES. Ever. Never use the "—" character (or "--" as a stand-in) to join or interrupt a sentence. Use a comma, a semicolon, a colon, parentheses, or just split it into two sentences. For number ranges, write "20 to 35%" or "20-35%" with a plain hyphen.
- NO MARKDOWN in the output. Plain prose only, the way it would look typed straight into a document or an essay box. No bold, no italics, no backticks, no "#" headings, and no markdown bullet or numbered-list syntax used for styling. Get emphasis from word choice and sentence structure, not symbols.
Last step before you hand anything back: scan the whole draft for the "—" character and for any "*", "_", "#", or backtick, and fix anything you find.
1. Snapshot
This writer is a friendly skeptic. They open by questioning something everyone takes for granted, explain it with a plain everyday analogy, and land on a short, blunt punchline. The register flexes, looser for opinion and tighter for the research snippet, but the engine is the same: question the assumption, make it concrete with a comparison, end on a line you remember.
2. Core voice principles
- Open by questioning the default. Most pieces start with a rhetorical question that
challenges a common belief.
"Why does everyone assume the newest phone is automatically the better buy?" "What actually happens to a memory while you sleep?"
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 First seen · 120 lines · 77 tokens per session scan A 497a31557529
writing-voice is a skill published in the GitHub repository 98ping/chip (2 stars, last pushed 9d ago), licensed MIT. It adds 77 tokens to every session and 1,403 once invoked, about $0.0004 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
release
发布 Usage4Claude 新版本时使用。当用户说“发布新版本 / 发版 / 出新版 / release / 打 tag 发布 / 准备发版材料”等，用本 skill 引导完成从收集变更、编写 CHANGELOG 与 RELEASENOTES、更新版本号、编译验证，到发版 commit、CI 自动发布的完整流程。.
capture-usage4claude-screenshots
Automate Usage4Claude interface screenshots with CleanShot X on macOS. Use when Codex needs to capture localized Usage4Claude menu-bar popover screenshots, switch Usage4Claude display/language settings, save files such as [email protected], or troubleshoot CleanShot/window-capture automation that depends on…
che-word-mcp
A Swift-native MCP server for Microsoft Word (.docx) document manipulation. Provides 83 tools for reading, writing, and modifying Word documents without requiring Microsoft Word installation.
project-setup
Scaffold a new client project folder from the client-project template, retrofit an existing client folder to the template structure, or reconcile a client folder's memory files after a thread loss. This is the client-engagement variant of the project-setup skill — for internal products, use…
topical-authority-map
Builds a 4-cluster Topical Authority Map from a seed keyword. Outputs an .xlsx spreadsheet with five tabs (Core Pages, AOR Pages, Linking Map, Buyer Journey, Publishing Order) plus a markdown strategy document. Interactive, asks the user to confirm central entity, source context, persona, classification, and gaps at…
dream
Consolidate and reorganize project memory (MEMORY.md) by invoking the dream-consolidator named subagent (Sonnet, pinned via the agent's model: frontmatter — NEVER pass a model: parameter yourself, it defeats the pin and runs the dream on expensive Opus). The subagent prompt is a CLOSED TEMPLATE: send its fields and…