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 soia-team/soia-open-skills --skill soia-meta-sync-skillsgit clone --depth 1 https://github.com/soia-team/soia-open-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/soia-team/soia-open-skills/soia-meta-sync-skills)<a href="https://agentmods.dev/skills/soia-team/soia-open-skills/soia-meta-sync-skills"><img src="https://agentmods.dev/badge/skills/soia-team/soia-open-skills/soia-meta-sync-skills/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/soia-team/soia-open-skills/soia-meta-sync-skills"><img src="https://agentmods.dev/badge/skills/soia-team/soia-open-skills/soia-meta-sync-skills.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 | $0.00038 | $0.01942 |
| Opus 5 | $0.00019 | $0.00971 |
| Sonnet 5 | $0.00008 | $0.00388 |
| Haiku 4.5 | $0.00004 | $0.00194 |
Grade A, and why
soia-meta-sync-skills 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 7d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
soia-meta-sync-skills
范围先行:默认不会选择全局、全宿主或全量。项目模式只写
<project>/.agents/skills;全局宿主目录仅在客户显式给出--scope global和--targets后处理。
客户可读说明
这个技能可以做什么
将一个已安装或本地的共享技能目录同步到用户选择的 AI 工具目录。它只创建或替换同名的软链接;先用 --dry-run 展示影响,再在已有明确授权时写入。同一任务内只有已展示影响并获客户明确批准、且包含 source、具体 target、action 以及删除/替换影响的完整计划,才可由 Finder、Installer 或 Release 传递而不重复询问;计划字段变化时重新确认受影响部分。
客户如何使用
提供源目录、--scope、目标粒度和技能范围。没有 --scope、--target-kind 或项目 Agent 选择时,脚本只返回 selection_required,不写入。
python3 skills/soia-meta-sync-skills/scripts/sync_soia_skills.py \
--source-dir <shared-skill-dir> \
--scope project --project-dir <project> --agents codex \
--target-kind skill --skills <skill-name> \
--dry-run
skill、domain、all 都支持;默认不全量。--skills '*' 和 --targets '*' 必须显式选择 all,先 dry-run;全宿主写入还需 --confirm-all-targets。使用 --exclude-skills a,b 可在本次运行中对每个选中 target 跳过并摘除这些技能的既有软链。
依赖与安装
claude plugin marketplace add soia-team/soia-open-skills
claude plugin install soia-meta@soia
只要这一个技能时,可用 npx 路线。注意技能会落进共享真源 ~/.agents/skills;若同时装了插件,同一技能会出现两份索引且各自漂移,建议二选一:
npx skills add soia-team/soia-open-skills -a <explicit-agent> -s soia-meta-sync-skills -y
依赖 Python 3 标准库和一个包含 SKILL.md 子目录的源目录。可选配置示例记录用户自己的 source/targets 和按 target 隔离的 excludes,命令行参数优先;它不替代本轮范围选择。配置文件放在:
~/.config/soia-skills/soia-meta-sync-skills/config.yml
SOIA_META_SYNC_SKILLS_CONFIG_FILE=<custom-config-path>
WorkBuddy 的装载单位是角色化专家而不是插件;全宿主选择也不覆盖它,需要单独安装,见 docs/install/workbuddy.md。
私密信息与中间数据
- 配置只保存客户选择的 source/targets 和 per-target excludes,不保存 API key、cookie、session 或其他凭据。
- 同步计划默认只打印到终端;实际写入的脱敏审计日志按“输出文件”约定轮转,且不记录密钥内容。
日志与完成回执
完成:<dry-run 或实际同步结果>。
日志摘要:
- source: <共享技能源>
- targets: <目标目录>
- linked/removed: <数量与名称>
- skipped/failed: <原因或无>
验证:<命令退出码、软链接解析或 dry-run>
问题与下一步:<确认、缺依赖或无>
安全边界
- 先展示 source、目标、将创建/替换/删除的链接;没有本轮明确写入授权时停在预览。仅选择字段齐全不构成写入批准;完整计划已展示影响并获客户明确批准后才可写入,扩大目标、宿主、粒度、source 或删除/替换范围时必须重新确认。
- 拒绝把 source 自身作为目标;不复制目录。
- 只处理
soia-*管理名和当前点名技能;绝不删除无关第三方技能。 - 默认清理指向不存在目标的一级
soia-*软链接;用--no-prune保留它们。
What ships with it
7 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.
- 7d ago Changed · +2 lines · -7 tokens per session 167e3173537e
- 12d ago First seen · 149 lines · 45 tokens per session scan A ff17a0a54959
soia-meta-sync-skills is a skill published in the GitHub repository soia-team/soia-open-skills (5 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,942 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
validate
Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with --migrate.
memex-sync
Sync Zettelkasten cards across devices via git.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
raytsystem-watch
Inspect video, audio, or supplied transcripts through raytsystem Tool Hub and return evidence-bound speech, visual, OCR, action, transition, and timeline findings. Use for /watch, a YouTube/Loom/public Zoom/direct media URL, a local video or audio file, a transcript, or requests such as "watch this video", "analyze…
research-workflow-orchestrator
Run a resumable end-to-end research workflow that automates low-risk work, pauses at explicit human decision gates, records provenance, and routes each stage to the appropriate research-hub skill or MCP tool.
literature-triage-matrix
Turn a list of papers (Zotero collection, Obsidian cluster, manual list) into a compact comparison matrix written to .research/literaturematrix.md, instead of generic per-paper summaries. Use when the user asks to "make a literature matrix", "compare these papers by method/data/limitations", or "decide which papers…