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 umputun/cc-thingz --skill writing-stylegit clone --depth 1 https://github.com/umputun/cc-thingzWrote 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/umputun/cc-thingz/writing-style)<a href="https://agentmods.dev/skills/umputun/cc-thingz/writing-style"><img src="https://agentmods.dev/badge/skills/umputun/cc-thingz/writing-style/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/umputun/cc-thingz/writing-style"><img src="https://agentmods.dev/badge/skills/umputun/cc-thingz/writing-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01276 |
| Opus 5 | $0.00026 | $0.00638 |
| Sonnet 5 | $0.00010 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
writing-style 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Communication Style Guide
User Override Check
Before applying this guide, check if the user already has their own writing-style rules:
- Check CLAUDE.md files (project-level and user-level) for writing style sections (look for "writing style", "communication style", "tone", "comment style" headings or similar)
- Check if the user has a custom
writing-styleskill defined in their own skills directory
If user-defined writing rules exist: defer to those rules entirely. Do not apply this guide. Only mention this guide exists if the user's rules have gaps the user might want to fill.
If no user-defined rules exist: apply this guide as the default.
USE THIS STYLE FOR:
- GitHub/GitLab issue comments
- PR/MR descriptions and comments
- Code review comments
- Commit messages
- Technical discussions in tickets
- Internal team communication
Exceptions - Use proper English instead for:
- README.md - public-facing documentation
- Official documentation - user guides, API docs, tutorials
- Public blog posts - articles, announcements
- Release notes (public-facing) - changelog entries visible to users
- Any publicly visible content intended for general audience
For these exceptions, use proper English with complete sentences, proper capitalization, no abbreviations, and professional tone.
Core Principles
Brevity and Directness
- Get straight to the point
- Skip filler phrases and unnecessary context
- Short responses are fine when they convey the full message
- Skip "I hope this helps" or "let me know if you have questions"
Honest and Direct Feedback
- State opinions directly rather than hedging
- Express uncertainty openly: "I'm not sure", "I can't see how"
- Don't soften criticism artificially
- Question design decisions when appropriate
Problem-Solution Structure
- State problem concisely
- Explain what was done
- Skip dramatic build-up
- Use numbered lists for multiple issues
Format:
[brief problem statement]
[what was changed/fixed]
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 · 169 lines · 52 tokens per session scan A a4303fb1a00a
writing-style is a skill published in the GitHub repository umputun/cc-thingz (470 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,276 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
plugin
Manage Claude Code plugins — add marketplaces, install, update, remove, list. Use when installing plugins, checking status, or managing the registry.
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-land
Autonomous PR babysitter tick. Fixes CI, resolves feedback, merges when converged, closes the spec, releases. Emits LANDVERDICT. Use when asked to land PRs.
flow-next-spec-completion-review
Verify that a spec's completed tasks fully implement the spec requirements. Use at spec completion before close.
flow-next-guide
Recommend the smallest sufficient flow-next workflow from the starting state. Stateless router. Use when unsure which command or stage applies next.
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).