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 hxy91819/mason-skills --skill large-task-orchestratorgit clone --depth 1 https://github.com/hxy91819/mason-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/hxy91819/mason-skills/large-task-orchestrator)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/large-task-orchestrator"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/large-task-orchestrator/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/hxy91819/mason-skills/large-task-orchestrator"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/large-task-orchestrator.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 | $0.00027 | $0.02378 |
| Opus 5 | $0.00014 | $0.01189 |
| Sonnet 5 | $0.00005 | $0.00476 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
large-task-orchestrator 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 today.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大型任务 driver
这是流程类 Skill,仅在用户显式调用 $large-task-orchestrator 时运行。它只接管已经通过
large-task-planning v2 校验的计划:脚本是控制面,Worker、Validator 和异常时的 Judge 都是经
bb-dispatch 创建的短生命周期 BB 线程。
开始前阅读相邻的 large-task-planning 计划格式、bb-model-routing
和联合设计。计划 JSON 与 Git 是权威状态;每个 (仓库, 计划) 的
.local/large-task-orchestrator/<topic-slug>/ 保存可回看的运行事实。
生命周期用法
- 先确定用户指定的计划;未指定时只能使用当前仓库唯一的计划。阅读仓库规则、
SPEC.md、STATUS.md,检查 分支、git status --short和git worktree list,保留并发改动。然后只对这个(仓库, 计划)查询状态:
python3 <orchestrator-skill>/scripts/large_task_driver.py status \
--plan <topic>/agent/plan.json --stories-dir <topic>/agent/stories
-
若
status显示 driver 仍在运行,把 completed/total、每张 in-progress Story 的阶段、线程 ID 和难度翻译给 用户;不要自己运行主循环,也不要读线程全文。若last_stop非空或有 blocked Story,说明事实,并只向用户索取 继续所需的最小决定。需要停止时使用stop [--wait];它只在当前run_once结束后退出,不会中断 BB 线程。 -
若没有运行中的 driver,用
start启动指定计划。start自己会先执行计划校验和bb-dispatch --dry-run, 然后在新 session 中派生后台run;本轮到此结束,向用户报告 pid、日志路径和后续状态命令。不要在本轮改用 前台run等待结果。
python3 <orchestrator-skill>/scripts/large_task_driver.py start \
--plan <topic>/agent/plan.json \
--stories-dir <topic>/agent/stories \
--repository <repo-root> \
--environment <bb-environment-id>
同一计划已有存活 pid 时 start 以退出码 4 拒绝重复启动;陈旧 pid 自动覆盖。不同仓库或同一仓库不同计划使用
独立的状态目录与锁,可以同时运行。计划中的 owner 保留 Worker 线程 ID;遗失计划本地状态时,driver 会从计划
和 BB 线程恢复。仅在排障或定时任务需要前台单次推进时才用 run 或 start --foreground 加 --once。
正常循环与异常
正常路径由 driver 选择 ready frontier、领取 Story、派 Worker、核对 Git 改动事实,再派 Validator 判断 Acceptance、Story 边界和 Worker 路径归属;通过后更新 Handoff、刷新投影并只 checkpoint Validator 确认归属的 Worker 路径。
发生 Worker blocked/failed、线程 error、待处理 interaction、空改动、报告无法解析或
Validator 多轮失败时,driver 才派 complex Judge。Judge 只能选择 retry、escalate、patch、
block、replan 或 stop。block 后继续其他 ready Story;replan 后重新校验计划;stop 或没有
ready Story 时退出并把最小原因写到 stderr。
不要手动篡改 driver 状态文件、Story 的 owner 或 Handoff 来跳过这些状态转换。要处理停下原因,先读 driver
status --json、计划状态和该计划的 jsonl;只有在既定 Goal 和授权内作出必要处理后,才在下一次本 Skill 调用时
按上述流程重新 start。需要凭据、权限、外部/破坏性动作、显著成本或稳定边界变更时才请用户决定。
What ships with it
6 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.
- today Changed · +22 lines a866a33fe9bf
- yesterday Changed · -21 lines · -4 tokens per session b29c8b80d92c
- 6d ago Changed · -4 lines 54186c0d1e2e
- 7d ago Changed · -56 lines · +4 tokens per session 0ea4f90c8a95
- 11d ago First seen · 202 lines · 27 tokens per session scan A 140f44893883
large-task-orchestrator is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 2,378 once invoked, about $0.0001 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…