agentleFS
maxipavlovicmaxipavlovic/agent-eye/skill/SKILL.md

eye

Skill4 starsChanged 4 days agoMITView on GitHub

Find, resume and tidy up Claude Code sessions with the eye board. Use when the user asks "where did we...", "which session...", "find the session...", "what was I doing...", "park this idea...", "mark this done...", or wants to know where a piece of work stands.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. catcatcatstudio/cat-skills★ 3same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run eye find --json <words> with the key words of the question (add --all to include archived and hidden sessions).

    line 14
  2. Distinctive:

    Do not paste the whole JSON.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

eye

eye (the agent-eye binary; eye is its alias) indexes every Claude Code session on this machine (title, folder, state, next step, outputs) and has an optional web board: eye board on turns it on (then eye board prints its URL), eye board off turns it off. It is off by default.

Finding a session

The user has the terminal picker for themselves (eye, or Ctrl-G in the shell; see docs/terminal.md). For your own lookups use the JSON search below.

Run eye find --json <words> with the key words of the question (add --all to include archived and hidden sessions). Answer briefly with, for the best hit or two:

  • title and folder (with branch if there is one)
  • state: the column and the one-line state
  • next step, if there is one
  • the resume command, exactly as resume_cmd gives it

Do not paste the whole JSON. If nothing matches, say so and try other words once.

To see what a session was about before resuming it, eye show <id> --conversation [-n 10] prints the last messages (your prompts and Claude's replies), and eye show <id> includes the tokens it used. eye resume <id> --fork --dry-run prints the command that resumes it as a new branching session (--fork-session).

Parking an idea

eye idea add "<title>" [--notes "<text>"] [--prompt "<text>"] stores an idea in the Ideas column. --notes is for the user and is never sent to Claude; --prompt is the first message the new session gets when the idea starts (without one, Claude opens in the folder and waits for the user). Write the prompt as a clear task for a fresh session that knows nothing of this one. The folder is the current working directory unless --dir <path> is given. eye idea edit <n> [--title] [--notes] [--prompt] [--dir] changes one (an empty value clears notes or prompt). eye idea ls lists them. Starting one is done from the board.

Marking a session

eye mark --current <status> [--next "<text>"] marks the session you are running in. Status is one of done, paused, waiting, needs-you, archive, auto (auto hands the card back to eye). For another session: eye mark <id> <status>.

Checking on something later

eye remind <id> <when> [--note "<text>"] brings a session (or an idea, as idea:<n>) back to Needs you at a time, for a reply that may not come or an idea to look at by a day. <when> is tomorrow, mon..sun, 30m, 4h, 3d, 1w, 2026-11-20 or "2026-11-20 14:00" (a day alone means 9:00). eye remind <id> --clear removes it and eye remind ls lists them. Everything stays on the machine; a desktop notice for a due one is off unless the user turned it on (eye remind notify on). Use it only when the user asks.

Confirm in one line what you changed.

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.