block-task

A task command for marking work as blocked and recording why it cannot continue. It also moves the task into a blocked folder.

In plain words
What is it for?
Use it when a task is stopped by unclear requirements, failed builds or tests, missing services, dependency problems, or a needed review or decision.
Why use it?
It keeps unfinished work from being mistaken for active work and preserves the problem details needed to resolve it.

Command for Claude Code

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.

agentmods
npx agentmods add commands/modelengine-group/fit-framework/block-task
Clone the repo
git clone --depth 1 https://github.com/ModelEngine-Group/fit-framework

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.03174
Opus 5 $0.00006 $0.01587
Sonnet 5 $0.00003 $0.00635
Haiku 4.5 $0.00001 $0.00317

Measured yesterday against content hash 25efc642c538, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

block-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 yesterday.

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.

.claude/commands/block-task.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Block Task Command

功能说明

当任务遇到无法继续的问题时,使用此命令标记任务为阻塞状态,记录详细的阻塞原因,并将任务移动到 blocked 目录,等待问题解决。

⚠️ CRITICAL: 状态更新要求

执行此命令后,你必须立即更新任务状态并移动任务目录。参见规则 7。

使用场景

何时使用此命令

在以下情况下应该标记任务为阻塞:

技术问题

  • ❌ 编译失败且无法修复
  • ❌ 测试失败且原因不明
  • ❌ 依赖库存在 Bug
  • ❌ 环境配置问题
  • ❌ 工具链问题

需求问题

  • ❓ 需求不明确,需要澄清
  • ❓ 发现需求冲突
  • ❓ 缺少必要的需求信息
  • ❓ 需要产品决策

资源问题

  • ⏳ 等待外部依赖
  • ⏳ 等待第三方 API 或服务
  • ⏳ 等待数据库迁移
  • ⏳ 等待基础设施就绪

决策问题

  • 🤔 需要架构决策
  • 🤔 需要安全审查
  • 🤔 需要性能优化方案选择
  • 🤔 需要人工审查和批准

何时不使用此命令

以下情况不应该标记为阻塞:

  • ✅ 代码审查发现问题 → 使用 /refine-task 修复
  • ✅ 实现遇到困难但可以解决 → 继续实施
  • ✅ 测试失败但原因清楚 → 修复测试
  • ✅ 文档不完整 → 完善文档

执行流程

1. 验证任务存在

检查任务文件是否存在:

ls -la .ai-workspace/active/{task-id}/task.md

如果任务不在 active 目录,检查是否已经在 blockedcompleted 目录。

2. 分析阻塞原因

在标记阻塞前,必须仔细分析并记录以下信息:

问题描述

  • 遇到了什么具体问题?
  • 问题出现在哪个步骤?
  • 问题的表现形式是什么?

根本原因

  • 为什么会出现这个问题?
  • 问题的根源是什么?
  • 是否有错误日志或诊断信息?

尝试的解决方案

  • 已经尝试了哪些方法?
  • 为什么这些方法没有解决问题?

需要的帮助

  • 需要谁来帮助解决?
  • 需要什么资源或信息?
  • 预计解决问题需要多长时间?

3. 更新任务状态 (CRITICAL)

必须更新 .ai-workspace/active/{task-id}/task.md

status: blocked
current_step: {当前步骤,保持不变}
updated_at: {当前时间,格式: yyyy-MM-dd HH:mm:ss}
blocked_at: {当前时间,格式: yyyy-MM-dd HH:mm:ss}
blocked_by: {当前AI}
blocked_reason: {简短描述阻塞原因}

在 task.md 中添加"阻塞信息"章节(在 "注意事项" 之前插入):

---

## ⚠️ 阻塞信息

### 阻塞概要

- **阻塞时间**: {当前时间}
- **阻塞步骤**: {current_step}
- **阻塞者**: {当前AI}
- **阻塞类型**: {技术问题/需求问题/资源问题/决策问题}
- **严重程度**: {高/中/低}
- **预计解决时间**: {预估}

### 问题描述

{详细描述遇到的问题,包括错误信息、日志、截图等}

### 根本原因

{分析问题的根本原因}

### 尝试的解决方案

1. **尝试方法 1**: {描述}
   - 结果: {失败/部分成功}
   - 原因: {为什么没有解决}

2. **尝试方法 2**: {描述}
   - 结果: {失败/部分成功}
   - 原因: {为什么没有解决}

### 需要的帮助

**需要谁**:{开发者/架构师/产品经理/运维/安全团队}

**需要什么**:
- 明确 XX 需求
- 解决 XX 技术问题
- 提供 XX 资源
- 做出 XX 决策

**附加信息**:
{任何有助于解决问题的额外信息}

### 解除阻塞条件

满足以下条件后可以解除阻塞并继续:
- [ ] 条件 1
- [ ] 条件 2
- [ ] 条件 3

### 备用方案

如果问题无法在合理时间内解决,可以考虑:
- 方案 1: {描述}
- 方案 2: {描述}

---

4. 移动到阻塞目录 (CRITICAL)

将任务从 active 目录移动到 blocked 目录:

# 确保 blocked 目录存在
mkdir -p .ai-workspace/blocked

# 移动任务目录
mv .ai-workspace/active/{task-id} .ai-workspace/blocked/

Read the full file on GitHub · 433 lines

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. yesterday First seen · 433 lines · 13 tokens per session scan A 25efc642c538

Subscribe to this mod's changes

block-task is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,117 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 3,174 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.