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 glebis/claude-skills --skill library-syncgit clone --depth 1 https://github.com/glebis/claude-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/glebis/claude-skills/library-sync)<a href="https://agentmods.dev/skills/glebis/claude-skills/library-sync"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/library-sync/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/glebis/claude-skills/library-sync"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/library-sync.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 | $0.00042 | $0.00799 |
| Opus 5.5 | $0.00017 | $0.00320 |
| Sonnet 5.5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
library-sync 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 2mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library Sync Skill
Manages the bilingual library at ~/Sites/agency-docs/content/docs/library/ with English (en/) and Russian (ru/) versions.
Commands
add <slug> — Add a new article to both languages
- Create the article in English first at
content/docs/library/en/<slug>.mdx - Translate to Russian at
content/docs/library/ru/<slug>.mdx - Add to both
meta.jsonfiles in the appropriate section - Run Russian stylistic review
- Verify both render correctly
sync — Check sync status between EN and RU
- List all files in
en/andru/ - Report files missing in either language
- Compare frontmatter titles (ensure they match conceptually)
- Flag articles updated in one language but not the other (compare git timestamps)
translate <slug> <from> <to> — Translate an article
- Read the source article
- Translate to target language
- Adapt examples and links for the target audience
- Run stylistic review if target is Russian
- Update meta.json
review-ru — Russian stylistic review
Run on all Russian library articles. Check for:
- Consistency: same terms used throughout (not mixing Агент/Эйджент)
- Natural Russian: not word-for-word translation from English
- Technical terms: keep English terms where standard (Git, MCP, API, CLAUDE.md)
- Links: internal links use
/library/ru/paths - Tone: educational but not condescending, informal "ты" address
update <slug> — Update an existing article in both languages
- Read the current version
- Apply changes to the primary language
- Sync changes to the other language
- Run Russian review if Russian was changed
File Structure
content/docs/library/
├── index.mdx # Landing page
├── meta.json # Top-level nav (separators + language folders)
├── en/
│ ├── meta.json # English article order with section separators
│ └── *.mdx # English articles
└── ru/
├── meta.json # Russian article order with section separators
└── *.mdx # Russian articles
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.
- 2mo ago First seen · 86 lines · 42 tokens per session scan A 6fd373963149
library-sync is a skill published in the GitHub repository glebis/claude-skills (409 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 799 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
library-sync compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| library-syncglebis/claude-skills | Skill | 409 | yesterday | MIT | A | 42 | Claude Code, Codex |
| global-data-get-{country}bobadilla-tech/requiems-api-skills | Skill | 2 | 1mo ago | MIT | A | 31 | Claude Code |
| global-data-post-resolvebobadilla-tech/requiems-api-skills | Skill | 2 | 1mo ago | MIT | A | 38 | Claude Code |
| detect-language-post-detect-languagebobadilla-tech/requiems-api-skills | Skill | 2 | 1mo ago | MIT | A | 32 | Claude Code |
| ios-appstore-release-managerflaqai/ios-application-development-skills | Skill | 5 | 2mo ago | MIT | A | 82 | Codex |
| pm-bilingualdannyhoang249-hub/pm-vietnamese-skill | Skill | 1 | 1mo ago | MIT | A | 53 | Codex |
| cm-safe-i18ntody-agent/codymaster | Skill | 56 | 2mo ago | none | A | 68 | Claude Code |