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 Moosphan/word-counter-skill --skill word-countergit clone --depth 1 https://github.com/Moosphan/word-counter-skillWrote 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/moosphan/word-counter-skill/word-counter)<a href="https://agentmods.dev/skills/moosphan/word-counter-skill/word-counter"><img src="https://agentmods.dev/badge/skills/moosphan/word-counter-skill/word-counter/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/moosphan/word-counter-skill/word-counter"><img src="https://agentmods.dev/badge/skills/moosphan/word-counter-skill/word-counter.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 | $0.00067 | $0.00492 |
| Opus 5 | $0.00034 | $0.00246 |
| Sonnet 5 | $0.00013 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
word-counter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Word Counter
Use the bundled script to produce a reproducible count instead of estimating from the model.
If the user asks in Chinese, run the script with --locale zh so the report is returned in Chinese. If the user asks in English, use --locale en. Only use --details when the user explicitly asks for detailed statistics.
Pick A Profile
- Use
zhfor Chinese-style content counting. - Use
enfor English-style word counting. - Use
mixedfor one total across Chinese and English text.
If the user is ambiguous, run mixed first and mention the zh and en alternatives.
Run The Script
For pasted content:
python3 "$HOME/.claude/skills/word-counter/scripts/word_counter.py" --profile mixed --locale en --format markdown --text "Hello world from OpenAI"
For a file:
python3 "$HOME/.claude/skills/word-counter/scripts/word_counter.py" --profile zh --locale zh --format markdown ./chapter-01.txt
Return A Clear Summary
Return this compact Markdown structure. Use the English example as the default format reference:
# Word Count Result
- Selected profile: `mixed` (Mixed-language count)
- Selected total: `1234`
- Applied formula: `mixed_count = cjk_chars + english_words + number_tokens + other_words`
| Metric | Value |
| --- | ---: |
| Chinese count | 1300 |
| English words | 45 |
| Mixed total | 1234 |
| Line count | 12 |
| Paragraph count | 4 |
For Chinese replies, use the same compact structure with Chinese labels. Do not show CJK characters, English words, or Number tokens unless the user explicitly asks for detailed statistics, in which case run with --details.
For rules and examples, read references/counting-rules.md.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 57 lines · 67 tokens per session scan A ac9cdaa68505
word-counter is a skill published in the GitHub repository Moosphan/word-counter-skill (1 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 492 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 2026-08-31.
Other skills, from other repositories
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
review-plan
Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the user asks to "review my plan", "check my plan", "critique my plan", or wants feedback on a plan.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".