agentleFS
Sign inStart free
saksham10arora-dotcomsaksham10arora-dotcom/everything-claude-codex/skills/catchup/SKILL.md

catchup

Skill74 starsChanged 9 days agoMITView on GitHub

Use when the user says "/catchup", "catch up", "what did I do in the other session", "read my last session", "continue from the app", "continue from terminal", or wants this Claude to read the full conversation history from another Claude Code surface (terminal <-> desktop Code tab)

26 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use wrapup, explain and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Skeln-ioSkill

    wrapup

    End-of-session closeout — commit, push, and optionally post a Slack summary. Use when you say "wrap up", "done for now", "save everything", or similar.

    Also in 3 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • MicrosoftSkill

    pr-review

    Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 4 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 4

    Distinctive

    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. Distinctive:

    Does NOT work in plain claude.ai chat or cloud sessions (no local file access).

    line 14
  2. Distinctive:

    Read the full output. Treat it as real context: it is the user's own prior conversation.

    line 35
  3. Very specific:

    If the other session SENT an email or pushed code but never logged it to personal/outreach/sent_log.md or .remember/hot.md, flag that gap …

    line 55
  4. Distinctive:

    Never invent what happened in the other session: only report what the transcript shows.

    line 57
  5. Distinctive:

    If no other session exists yet, say so plainly.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “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

CATCHUP: cross-surface conversation continuity

Two Claude Code surfaces (terminal CLI and the desktop "Code" tab) do NOT share live memory, but they both write full session transcripts to the same folder on disk. This skill reads those transcripts back in FULL (not a summary) so the current Claude can see exactly what happened in the other surface.

Works both directions, as long as both surfaces opened the SAME vault folder. Does NOT work in plain claude.ai chat or cloud sessions (no local file access).

Step 1: Run the reader

Pass the user's argument straight through. No argument means "latest".

python3 ~/.claude/skills/catchup/catchup.py <ARG>

Argument mapping:

  • (none) / "latest" -> most recent OTHER session, full text
  • a number N -> last N other sessions, full text
  • "all" -> every past session (warn it is heavy before running)
  • "list" -> just a table of recent sessions, no bodies
  • any other word -> sessions mentioning that keyword

The script auto-excludes the live/current session, so it never reads itself.

Step 2: Absorb and orient

Read the full output. Treat it as real context: it is the user's own prior conversation. Pull out what matters: decisions made, things drafted or sent, open threads, anything unfinished.

Step 3: Brief the user

Output a short recap of the other session(s):

Caught up from [date] session ([N] messages)

  • What happened: [1-3 bullets]
  • Left unfinished: [anything open]
  • Sent / shipped: [emails, commits, pushes: flag if not logged to the vault]

Where do you want to pick up?

Rules

  • Full fidelity by default. If the user wants everything, use all and accept the cost.
  • If the other session SENT an email or pushed code but never logged it to personal/outreach/sent_log.md or .remember/hot.md, flag that gap and offer to log it.
  • Never invent what happened in the other session: only report what the transcript shows.
  • If no other session exists yet, say so plainly.

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.

Check your setup, free