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/coracoo/zspace_skill/rag-managernpx skills add coracoo/zspace_skill --skill rag-managergit clone --depth 1 https://github.com/coracoo/zspace_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/coracoo/zspace_skill/rag-manager)<a href="https://agentmods.dev/skills/coracoo/zspace_skill/rag-manager"><img src="https://agentmods.dev/badge/skills/coracoo/zspace_skill/rag-manager.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 | $0.00144 | $0.01029 |
| Opus 5 | $0.00072 | $0.00515 |
| Sonnet 5 | $0.00029 | $0.00206 |
| Haiku 4.5 | $0.00014 | $0.00103 |
Grade A, and why
rag-manager 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 4d 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
RAG Manager — 语义搜索索引管理
概述
管理 NAS 上 RAG docker daemon(<nas_ip>:8000,bge-small-zh-v1.5 + sqlite-vec)的索引生命周期。
前置:nas-setup skill(验证 NAS 登录 + RAG daemon 在线)。
依赖 MCP tool:
index_status()— 索引概况(model/chunks/db_size)reindex(scope, full)— 重建索引semantic_search(query, scope, top_k)— 按 query 搜索(验证索引用)
RAG 不会自动扫描 NAS 文件。需要手动 reindex 或 NAS cron 定时触发。
工作流
场景 1:门控检查(label-manager RAG 的前置)
触发:label-manager 的 RAG 依赖 skill 被加载时,先调 rag-manager 做门控。
步骤:
- 调
index_status()→ 拿chunks、model、db_size - 如果
chunks == 0:调reindex(scope="files", full=true)→ 等完成后重查 status - 如果
error或 daemon 不通:返回错误,"RAG daemon 未就绪,请先部署 rag-server docker" - 如果
chunks > 0:门控通过,告诉调用方"RAG ready,chunks=X"
场景 2:用户说"更新 RAG 索引"
触发:"重建 RAG 索引"、"reindex"、"把 NAS 文件重新索引"、"RAG 搜不到新文件"
步骤:
- 调
index_status()看当前状态 - 调
reindex(scope="files", full=true)→ 同步阻塞(大目录几分钟) - 调
index_status()确认 chunks 数量增加 - 报告:已索引 X chunks,共 Y MB
场景 3:用户说"去掉某个文件的索引"
触发:"把 XX 文件从 RAG 索引里移除"、"unindex"
步骤:
- 当前 MCP 无
unindextool。走 rag-server HTTP API:POST /unindex {source_type, source_path} - 确认状态
/status→ chunks 减少
场景 4:用户说"配置 RAG 扫描范围"
触发:"RAG 只索引教材目录"、"让 RAG 扫更多目录"
步骤:
- 编辑
rag-server/.env的SCAN_ROOTS和NAS_RAG_PATH_MAP - 调
reindex(scope="files", full=true)应用新范围 - API 不暴露修改配置端点(需 SSH 或 docker compose restart)
跟 label-manager 的 RAG 分工
| 能力 | 用哪个 |
|---|---|
| 索引状态门控 | rag-manager |
| 重建索引 | rag-manager |
| 内容语义搜索 | label-manager(RAG 场景) |
| 搜索结果打标签 | label-manager → MCP save_file_label |
| 文件内容浏览 | label-manager(RAG 场景) |
label-manager 场景 6 步骤 2 改为:加载 rag-manager skill → 门控检查通过 → 继续。
关键约束
reindex是同步阻塞的(大目录几分钟),期间 MCP 会一直等待,LLM 应提示用户耐心等SCAN_ROOTS在rag-server/.env里,修改需要容器重启:docker compose restart- RAG daemon 部署在 NAS docker 上(不是本地),
/status优先走http://<nas_ip>:8000/status - 索引数据在
rag-server/data/(sqlite-vec),体积随文件数线性增长
What ships with it
1 file 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.
- 4d ago First seen · 86 lines · 144 tokens per session scan A 9f1efa334ceb
rag-manager is a skill published in the GitHub repository coracoo/zspace_skill (19 stars, last pushed 28d ago), licensed MIT. It adds 144 tokens to every session and 1,029 once invoked, about $0.0007 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
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
peek
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…