README

A set of Claude Code slash commands for the cloudwego/abcoder project. The commands create structured coding-task documents, design implementation plans, and check those plans against the codebase.

In plain words
What is it for?
Use /abcoder:task to create a task file, /abcoder:schedule to design a minimal-change solution, and /abcoder:recheck to test that plan's technical details.
Why use it?
They turn vague development requests into documented tasks and reviewable plans before code is written.

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/cloudwego/abcoder/readme
Clone the repo
git clone --depth 1 https://github.com/cloudwego/abcoder

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 880 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.00880
Opus 5 $0.00000 $0.00440
Sonnet 5 $0.00000 $0.00176
Haiku 4.5 $0.00000 $0.00088

Measured 2d ago against content hash 6dc9feb2832c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 涉及 curl 时提供具体命令(请求头、请求体、URL、响应结构)
internal/cmd/assets/.claude/commands/README.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Commands

Claude Code 斜杠命令定义,用于规范化和自动化开发工作流。

命令说明

/abcoder:task - 创建编码任务

创建 CODE_TASK 文档,规范化编码需求描述。

执行流程:

  1. 创建 ./task/{{MMDD}}/ 目录
  2. 读取模板 {{CLAUDE_HOME_PATH}}/.claude/tmpls/ABCODER_CODE_TASK.md
  3. 根据任务上下文填充模板,生成 ./task/{{MMDD}}/{{NAME}}__CODE_TASK.md
  4. 列出外部依赖包(如有)
  5. 提示创建成功

使用示例:

/abcoder:task Feature_Auth     → 创建 ./task/1231/Feature_Auth__CODE_TASK.md
/abcoder:task Bugfix-Api       → 创建 ./task/1231/Bugfix_Api__CODE_TASK.md

CODE_TASK 格式要求:

  • action: create/modify/delete
  • 文件路径准确
  • 涉及 SDK 时指定 Package/Method 名称
  • 涉及 curl 时提供具体命令(请求头、请求体、URL、响应结构)
  • 提供具体get_ast_node入参、验证方法

/abcoder:schedule - 设计实现方案

使用 mcp__abcoder 分析代码库,设计技术实现方案。

执行流程:

  1. mcp__abcoder__get_repo_structure 开始
  2. 下钻到 mcp__abcoder__get_ast_node 查看细节
  3. 分析依赖关系和调用链
  4. 设计最小改动、最大化复用的方案

Guardrails:

  • 最大化复用已有功能
  • 优先采用最小改动方式
  • 限制修改影响面
  • 找出模糊细节并提出问题
  • 禁止编写代码,禁止使用 agent

/abcoder:recheck - 技术方案核对

批判性检查 CODE_TASK 的技术可行性。

执行流程:

  1. mcp__abcoder__get_repo_structure 开始
  2. 使用 mcp__abcoder 核对技术细节
  3. 下钻到 mcp__abcoder__get_ast_node 粒度验证

检查项:

  • 方案是否可实现需求
  • 是否存在技术风险
  • 是否最大化复用已有功能
  • 是否最小化改动

模板文件

ABCODER_CODE_TASK.md

编码任务模板,定义任务清单格式。

核心要素:

1. [ ] 任务描述
   - file: 文件路径
   - action: create/modify/delete
   - 技术规格(SDK Method / curl JSON / IDL结构 / `get_ast_node` 调用参数)

核心理念 - 直接使用原则:

  • 编写 CODE_TASK 时预先使用 mcp__abcoder 分析
  • 提供完整的 get_ast_node 调用参数
  • SubAgent 直接执行,无需重新分析

工作流示意

用户需求
    │
    ▼
/abcoder:schedule ──────────────→ 设计方案(abcoder分析)
    │                            │
    ▼                            ▼
/abcoder:task ────────→ CODE_TASK(含技术规格)
    │                            │
    ▼                            ▼
/abcoder:recheck ─────→ 方案核对(abcoder验证)
    │                            │
    ▼                            ▼
coding-executor ──────→ 执行实现

文件位置

{{CLAUDE_HOME_PATH}}/.claude/
├── commands/
│   ├── abcoder:task.md
│   ├── abcoder:schedule.md
│   └── abcoder:recheck.md
└── tmpls/
    └── ABCODER_CODE_TASK.md

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 0 tokens per session scan A 6dc9feb2832c

Subscribe to this mod's changes

README is a command published in the GitHub repository cloudwego/abcoder (390 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 880 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.