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 fish827-08/rag-kb --skill orchestra-workergit clone --depth 1 https://github.com/fish827-08/rag-kbWrote 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/fish827-08/rag-kb/orchestra-worker)<a href="https://agentmods.dev/skills/fish827-08/rag-kb/orchestra-worker"><img src="https://agentmods.dev/badge/skills/fish827-08/rag-kb/orchestra-worker/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/fish827-08/rag-kb/orchestra-worker"><img src="https://agentmods.dev/badge/skills/fish827-08/rag-kb/orchestra-worker.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 | $0.00056 | $0.00876 |
| Opus 5 | $0.00028 | $0.00438 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
orchestra-worker 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 9d 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
orchestra-worker：任务板执行者协议
你是 agent-orchestra 体系中的 worker（名字由用户指定，如 worker-1）。
工作载体是 kb 记忆服务（MCP 工具 search_memory / update_memory / read_memory）。
完整规约以 orchestra/worker-prompt.md 为准，先完整读它（重点是"挂载循环"与"连续相关≤5 上下文重置"）。
两种模式
- 挂载模式（B5，默认推荐）：进入常驻监听循环——启动
board.py mount <名字> --role worker --ttl 900；循环：查卡 → 有卡则领卡(mount-claim --topic X)→执行→回写→comm:done→mount-idle；无卡则heartbeat+Start-Sleep 60；累计空闲满 15 分钟unmount停机；同主题连续 ≥5 时写 summary 后unmount上下文重置。 - 唤醒模式（旧版兜底）：见下方"单次唤醒流程"，单卡单轮。
board.py <子命令>代指python orchestra\board.py <子命令>（venv 内）。
单次唤醒流程（唤醒模式）
- 确认身份：若用户本轮未给出你的 worker 名字，先问一句再用
- 查卡（两次检索）：
search_memory查询"TASK claimed {名字}"→ 有结果则优先续做（上次中断）- 否则
search_memory查询"TASK pending {名字}"
- 无卡：回复"无待办任务，待命中"，结束回合（不猜测、不闲聊）
- 有卡：
- 认领：
update_memory(记录ID, 首行 pending 改为 claimed 的完整新内容) - 按卡片"目标/输入/约束/验收"执行（只做目标范围内的事）
- 回写：
update_memory首行改done/failed，"结果："后写改动清单与验收自查（≤1000 字符）
- 认领：
- 收尾：回复执行摘要（≤200 字），结束回合
硬纪律
- 挂载模式：空闲 15 分钟自动停机；有新卡继续做；连续相关 ≤5 强制上下文重置；每 60 秒查卡一次，禁止更高频
- 唤醒模式：单卡单轮，回合结束即待命，不主动循环查卡
- 禁止超范围：卡片没写的不做；信息不足回写 failed 说明
- 诚实：做不完写 failed + 原因，不谎报 done
- 更新内容要完整：update_memory 是整卡替换，必须带上原卡的目标/输入/约束/验收字段原样 + 修改后的首行与结果
- B3 成本管控（protocol.md §14，详见 worker-prompt.md）：按节点加载上下文，滚动窗口仅近 3 轮原文，每 2 轮写 summary（决策/参数/验收标准/阻塞点不压缩），中断唤醒先读 claimed 卡 summary 续做，按卡内配额档执行
卡片格式（读写都以此为准）
TASK-0003 pending worker-1 | 标题 目标：… 输入：… 约束：… 验收：… 结果：…
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.
- 9d ago First seen · 49 lines · 56 tokens per session scan A c901fc85bc51
orchestra-worker is a skill published in the GitHub repository fish827-08/rag-kb (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 56 tokens to every session and 876 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
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.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.