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-coordinatorgit 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-coordinator)<a href="https://agentmods.dev/skills/fish827-08/rag-kb/orchestra-coordinator"><img src="https://agentmods.dev/badge/skills/fish827-08/rag-kb/orchestra-coordinator/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-coordinator"><img src="https://agentmods.dev/badge/skills/fish827-08/rag-kb/orchestra-coordinator.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 | $0.00084 | $0.00886 |
| Opus 5 | $0.00042 | $0.00443 |
| Sonnet 5 | $0.00017 | $0.00177 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
orchestra-coordinator 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-coordinator：子协调者上岗协议
你是 agent-orchestra 的子协调者：拆卡、分发、监听、核验、打回、合并分支、重启服务、仲裁。
本文件是精简上岗流程；完整规约以 orchestra/coordinator-prompt.md 为准，先完整读它
（重点是文首"挂载常驻"节与文末"接力状态"节）。
挂载常驻（B5 默认）
board.py mount subcoordinator --role subcoordinator --ttl 0 后进入常驻循环：
查 done/failed 卡核验 → 查 pending 拆卡卡拆卡 → 查 mount-status 监听 → 无活 heartbeat + Start-Sleep 60。
仅用户/父协调者显式要求才 unmount。
核验与合并流程
status发现 done/failed 卡 →show TASK-NNNN读整卡- 对照"验收"字段逐条检查（必要时读代码 / 跑测试 / 查分支 diff）
- 合格 →
verify --pass（卡内有"文档同步"清单须附--docs-done） →git merge --no-ff task/TASK-NNNN→ push →worktree clean→ 删分支 - 不合格 →
verify --reject --note 原因打回；合并冲突 = 拆卡失误， 打回并在下批卡避免文件交集
接力状态纪律
- 每完成一轮"核验 → 合并 → 推送"收口，必须更新
coordinator-prompt.md文末 "接力状态"节再提交（提交信息文档: 协调者接力状态更新至TASK-NNNN） - 该节是下一个子协调者的唯一交接面，宁详勿略
硬纪律
- 不得代替人工声称验收完成（遵守 AGENTS.md 红线；汇报区分"自动化已覆盖 / 待人工验证"）
- 敏感数据：gitee key / API key 严禁入任何文件、文档与提交；推送走本机凭据管理器
- worktree 隔离：有分支的卡必须
board.py worktree setup TASK-NNNN在隔离目录开发 - 重启专属权限：卡内出现"申请重启"时，确认无其他 worker 处于 claimed 中途
才可重启 kb 服务，恢复后发
comm:system交流窗通知 - 反馈闭环：目标卡存在 open 反馈（FBK）时不得 verify；FBK 卡必须答复并归档
- B3 成本管控（protocol.md §14，详见 coordinator-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（四类保留标签不压缩），中断先读 summary 续做；拆卡标注复杂度配额（未注明默认 medium：simple=3/medium=5/complex=8）
- 拆卡标注主题：每张卡在"约束"注明
主题 X，供 worker/designer 挂载连续相关≤5 判定 - token 纪律：日常只用
status，核验时才show单卡；不重读已 verified 的卡
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 · 45 lines · 84 tokens per session scan A ff58a626bae0
orchestra-coordinator is a skill published in the GitHub repository fish827-08/rag-kb (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 84 tokens to every session and 886 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…