agentleFS
patrick-fupatrick-fu/awesome-skills/codex-session-naming/SKILL.md

codex-session-naming

Skill69 starsChanged 11 days agoMITView on GitHub

Maintain clear, accurate titles for top-level Codex App tasks at entry, meaningful changes, and wrap-up. Excludes ChatGPT chats and subagents.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep titles short, recognizable, and faithful to the conversation.

    line 10
  2. Distinctive:

    Use 1–2 useful scope tags and two parts:

    line 18
  3. Distinctive:

    Keep it concise rather than listing intermediate actions.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codex Session Naming

Keep titles short, recognizable, and faithful to the conversation. Use the user's language and supplied names; preserve IDs and terminology. Explicit format requests override defaults.

Title

<state> [tags] <mandate> · <focus>

Use 1–2 useful scope tags and two parts:

  • Mandate: the overall task or topic. Preserve through follow-up questions, detours, experiments, and approach changes. Replace for a new task after completion, or the user's clear replacement or cancellation.
  • Focus: the meaningful current result, bottleneck, decision, or next step. Keep it concise rather than listing intermediate actions.

Updates

At entry, meaningful state changes, and wrap-up, compare the title with the task: keep it while accurate; otherwise update it. Routine tool calls need no update. Reuse task facts and results already in context; naming introduces no new verification or coordination work.

State

Express who acts next and the current task state from established facts. A finished turn is not a completed task.

  • 🏁 mandate completed
  • ☑️ agreed checkpoint reached; work parked
  • 🔀 unfinished work handed to an accepted successor
  • 🙋 user decision, authorization, or action
  • 🕒 time, device, review, build, or external system
  • ⛔ no valid path
  • ⏸️ user pause
  • ⏳ owned queue not started
  • 🏃 Agent-owned active work; a self-explanatory action emoji also fits

Controllers

Established global controllers use 🕹️ <scope or name>; project controllers use 🗂️ <project or name>. Keep the role and name stable during routine progress; prefix 🏁 or 🔀 only for established completion or outgoing handoff.

Authority

Rename your own session without confirmation; controllers may rename owned workers. First bulk rename needs user authorization. Naming does not archive or transfer ownership.

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.

Reviews can't be read right now.

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.