agentleFS
0mlkrizzz655335v0mlkrizzz655335v/claude-skills-zh/skills/dev-env/statusline/SKILL.md

statusline

Skill2 starsChanged 5 months agoMITView on GitHub

状态栏配置。配置 Codex 或兼容 CLI 的状态栏。

Files
SKILL.md

CLI Status Line

Configure the status line of the user's Codex or compatible agent CLI. Inspect the executable/version and existing configuration before choosing the schema. A request about the Codex Desktop interface is not automatically a request to edit a CLI config file.

For a runtime that supports command-based statusLine in ~/.cursor/cli-config.json, read command status-line format. For another runtime, use its documented status-line settings or UI and the installed openai-docs skill when applicable. Do not create .cursor/cli-config.json merely because the target has a similar product name.

Preserve unrelated settings and back up the target file. Resolve the actual configuration path from the runtime/environment. Select only the fields the user wants to display; handle missing and null payload fields without inventing usage data.

For a command status line, use an interpreter available to that CLI process and valid native quoting. On Windows, do not assume Bash/jq or executable shebang support. Keep execution fast, avoid network calls, and never expose tokens, raw credentials, or sensitive transcript contents.

Validate the configuration and exercise the renderer/script with representative normal and missing-field inputs. Confirm the active CLI loads the change when possible; report separately if only configuration/script output was verified.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.