large-task-orchestrator

large-task-orchestrator is a skill for Claude Code, Codex from hxy91819/mason-skills. It costs 27 tokens per session (2,995 once invoked), scanned A, original, MIT.

An orchestration workflow for carrying out an existing large-project plan through separate worker and validator agents. The orchestrator tracks dependencies, dispatches stories, gathers handoffs, and integrates results.

In plain words
What is it for?
Use it to run planned engineering stories, send each story to a dedicated worker, have another agent validate it, and manage fixes, integration, and user decisions.
Why use it?
It keeps implementation and validation responsibilities separate and prevents one work session from mixing unrelated stories. Progress remains tied to the plan and its evidence.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to run planned engineering stories, send each story to a dedicated worker, have another agent validate it, and manage fixes, integration, and user decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hxy91819/mason-skills/large-task-orchestrator
Install

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.

Any agent
npx skills add hxy91819/mason-skills --skill large-task-orchestrator
Clone the repo
git clone --depth 1 https://github.com/hxy91819/mason-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for large-task-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/hxy91819/mason-skills/large-task-orchestrator/github.svg)](https://agentmods.dev/skills/hxy91819/mason-skills/large-task-orchestrator)
Your own site
<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.

agentmods 80×15 button for large-task-orchestrator

Your own site · 80×15
<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>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.02995
Opus 5.5 $0.00011 $0.01198
Sonnet 5.5 $0.00005 $0.00599
Haiku 4.5 $0.00003 $0.00299

Measured 1mo ago against content hash 5d2ba9d7dbbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/large_task_driver.py, scripts/large_task_report.py, tests/test_large_task_driver.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

common-skills/large-task-orchestrator/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 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 BB 线程。Worker 和 Validator 按轮次独立;每张 Story 的 Judge 使用一个独立会话, 后续裁决在同一会话续聊。

开始前加载 $large-task-planning 与 $bb-model-routing。使用宿主返回的两个 Skill 根目录分别定位 scripts/epic_story.py 和 scripts/bb-dispatch,不要假设它们与本 Skill 相邻。需要理解整体职责时,按 $large-task-planning 的指引读取它拥有的联合设计。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

  1. 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 \
  --planning-script <large-task-planning-skill>/scripts/epic_story.py \
  --dispatch <bb-model-routing-skill>/scripts/bb-dispatch
  1. 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。

  2. 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> \
  --planning-script <large-task-planning-skill>/scripts/epic_story.py \
  --dispatch <bb-model-routing-skill>/scripts/bb-dispatch \
  --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。driver 因需要用户处理(退出码 3)、受控停止或全部完成而退出时,会向启动它的 BB 线程发一条 简短消息(结论、需要用户决定什么、status 命令);线程 ID 取 --notify-thread 或环境变量 BB_THREAD_ID,都没有则静默跳过。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。

Read the full file on GitHub · 165 lines

Files

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.

Changes

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.

  1. 1mo ago Changed · +14 lines 5d2ba9d7dbbb
  2. 1mo ago Changed · -1 lines 5098364b88a2
  3. 1mo ago Changed · +5 lines 830ba846015b
  4. 1mo ago Changed · +4 lines 51457fe63f8c
  5. 1mo ago Changed · +22 lines a866a33fe9bf
  6. 1mo ago Changed · -21 lines · -4 tokens per session b29c8b80d92c
  7. 2mo ago Changed · -4 lines 54186c0d1e2e
  8. 2mo ago Changed · -56 lines · +4 tokens per session 0ea4f90c8a95
  9. 2mo ago First seen · 202 lines · 27 tokens per session scan A 140f44893883

Subscribe to this mod's changes

large-task-orchestrator is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 2,995 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

large-task-orchestrator compared with skills from other repositories

large-task-orchestrator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
large-task-orchestratorhxy91819/mason-skillsSkill3todayMITA27Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code