360 Secure SkillHub
360 安全技能中心

along-plan

在计划模式下仅使用只读工具探索代码库,输出带 Plan: 标题的编号步骤,并保存含 TODO 与验收标准的 Markdown 计划文件;执行阶段用 [DONE:n] 标记步骤完成。

orangon
orangon
热度 33.01
最近更新 2026-05-11 17:38:29
分类:开发依赖:代码执行 / 读写文件应用场景:代码审查 / 任务管理 / 工作流

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add along-plan
Metadata
name
along-plan
description
Read-only exploration and planning skill for safe code analysis. This skill should be used when the user asks to enter plan mode, analyze before changing, create a plan first, or wants a safe exploration phase before making edits. Enforces read-only tool access, produces a numbered plan under a Plan: header, and tracks step completion with [DONE:n] markers during execution.

Along Plan

Explore

  • Only use read, grep, glob, bash (bash restricted to safe commands — see references/safe-commands.md)
  • Do NOT use edit or write, except to save the plan document (see below)

Output the plan under an exact Plan: header:

Plan:
1. Step one
2. Step two
3. Step three

Then save it to docs/plan-<topic>.md or doc/plan-<topic>.md(whichever exists) using write:

# Plan: <topic>

## TODO
- [ ] 1. Step one
- [ ] 2. Step two

## Acceptance Criteria
- Observable outcome that confirms the plan succeeded
- Edge cases or constraints that must hold
  • references/safe-commands.md — bash allowlist/blocklist for plan mode