os-task

os-task is a command for Claude Code from CronusL-1141/AI-company. It costs 18 tokens per session (736 once invoked), scanned A, original, MIT.

A command for managing an AI Team OS task wall: viewing tasks, adding new work, and checking task details and progress.

In plain words
What is it for?
Use it to review recommended work, filter tasks by team, create and prioritize tasks, or inspect a task’s status, history, and execution trace.
Why use it?
It makes project priorities, ownership, dependencies, and progress visible in one place.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Part of the ai-team-os plugin — 5 skills, 8 commands, 25 agents, 15 hooks, 1 MCP server shipped together

Good fit Use it to review recommended work, filter tasks by team, create and prioritize tasks, or inspect a task’s status, history, and execution trace.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cronusl-1141/ai-company/os-task
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.

Clone the repo
git clone --depth 1 https://github.com/CronusL-1141/AI-company

Made for: Claude Code.

Or install ai-team-os, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 25 agents, 15 hooks, 1 MCP server.

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 os-task

README.md
[![agentmods](https://agentmods.dev/badge/commands/cronusl-1141/ai-company/os-task/github.svg)](https://agentmods.dev/commands/cronusl-1141/ai-company/os-task)
Your own site
<a href="https://agentmods.dev/commands/cronusl-1141/ai-company/os-task"><img src="https://agentmods.dev/badge/commands/cronusl-1141/ai-company/os-task/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 os-task

Your own site · 80×15
<a href="https://agentmods.dev/commands/cronusl-1141/ai-company/os-task"><img src="https://agentmods.dev/badge/commands/cronusl-1141/ai-company/os-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 736 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 $0.00018 $0.00736
Opus 5 $0.00009 $0.00368
Sonnet 5 $0.00004 $0.00147
Haiku 4.5 $0.00002 $0.00074

Measured 10d ago against content hash d91606f97a47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

os-task 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 10d 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.

plugin/commands/os-task.md · 74 lines

What it actually says

/os-task — 任务管理

帮助用户管理 AI Team OS 的任务墙。

用法

  • /os-task — 查看当前项目的任务墙
  • /os-task <team_id|团队名> — 只看某支队的任务墙
  • /os-task new <描述> — 把一件事放上任务墙
  • /os-task <task_id> — 查看单个任务详情与进展记录

操作流程

无参数:看任务墙

调用 task_list_project()(不传参即用当前活跃项目)。返回按 short/mid/long 三档分组、组内按 score 排序的任务,直接照此顺序展示——这个排序就是"接下来该 做什么"的答案,不要自行重排。

只看一支队时传 task_list_project(team_id="<队名或ID>")

new 模式:把任务放上墙

  1. 确认两件事(用户已给出就不要再问):任务描述、目标团队。 团队用 team_list() 取;只有一支活跃队就直接用它。
  2. 调用 task_create(...);若要立刻挂到某支队名下并带优先级/时间档, 用 task_run(team_id=..., description=..., priority=..., horizon=...)
  3. 任务上墙 ≠ 有人在做:OS 不会自己执行任务。要推进就用 CC 的 Agent(...) 派人,并在 prompt 里写明 task_id,让其用 task_memo_add 回写进展。

查看模式:任务详情

  1. task_status(task_id) — 状态、归属、依赖、结果。
  2. task_memo_read(task_id) — 历史进展记录(接手前必读)。
  3. 想看完整时间线:task_execution_trace(task_id);要连带耗时/步数统计就 task_execution_trace(task_id, include_stats=True)

输出格式

任务墙

## 项目任务墙(short / mid / long)

### short
| 优先级 | 任务ID | 标题 | 状态 | 分配给 |
|--------|--------|------|------|--------|
| critical | 3f2a… | 修复登录 500 | running | backend-dev |

任务详情

## 任务 3f2a…

状态: running   优先级: critical   归属: dev-team
依赖: 无        分配给: backend-dev

### 进展记录
- [progress] 已复现,定位到 session 中间件
- [decision] 采用 A 方案,理由…

注意

  • 所有输出使用中文
  • 状态用中文标记:pending=待处理, running=进行中, blocked=被阻塞, completed=已完成, failed=失败
  • 任务墙默认是精简视图(view: "compact")——那是有意裁剪,不是字段缺失; 要全字段传 fields="all",要单个任务的完整信息用 task_status
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. 10d ago First seen · 74 lines · 18 tokens per session scan A d91606f97a47

Subscribe to this mod's changes

os-task is a command published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 736 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 2026-08-30.