菜单
Use when the task is codebase exploration rather than modification, and you need a fast, read-only search pattern that starts broad when location is unknown, narrows when location is known, and parallelizes independent searches
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when verifying implementation work and the failure mode is superficial approval, code-reading in place of execution, or over-trusting a passing test suite without trying to break the change
Use when coordinating multi-step work across workers or subagents, especially when research, implementation, and verification should be split while the main agent stays responsible for synthesis and user communication
Use when deciding what information belongs in memory, how to classify it, and what must not be saved because it is derivable from the repo, git history, or current task context
Use when deciding whether shell commands are truly read-only, safe for concurrent execution, and free of path, git, redirection, or command-shape risks that should force a stricter permission path
Use when the real risk is not lack of knowledge but self-justifying shortcuts such as explaining instead of running commands, skipping the hard part first, or deciding on your own that verification would take too long
Use when maintaining session notes that must preserve a fixed markdown template, stay within section and total token budgets, and remain useful after compaction or resume
基于 SOC 职业分类
| name | lightweight-explorer |
| description | Use when the task is codebase exploration rather than modification, and you need a fast, read-only search pattern that starts broad when location is unknown, narrows when location is known, and parallelizes independent searches |
Explore cheaply. This pattern is based on the built-in explore agent in src/tools/AgentTool/built-in/exploreAgent.ts and the read-only command rules in the bash tooling.
The explorer's job is to find, read, and report, not to edit.
A lightweight exploration task should be:
If the task needs edits, stop using this skill and switch to an implementation workflow.
Start broad:
Search multiple angles in parallel when they are independent.
Read narrowly:
Do not keep globbing the whole repo when you already know the file.
Change search axis instead of repeating the same failed query:
Do not:
Use only read-only tools and commands.
Return:
Keep it concise. Exploration should shorten the path to the next decision.
You have applied this skill correctly when the task stays read-only, the search narrows as evidence improves, and the result gives the next agent enough context without paying modification cost.
