agentleFS
apappascsapappascs/claude-code-sessions/skills/session-resume/SKILL.md

session-resume

Skill2 starsChanged 27 days agoMITView on GitHub

Generates a context recovery prompt from a past Claude Code session so a new session can pick up where it left off. Use when the user says "resume from", "pick up where I left off", "continue that session", "context recovery", or wants to start a new session with context from an old one.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use eval-harness.

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.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    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:

    If the user provides a session ID, resolve it.

    line 16
  2. Very specific:

    When a user runs claude --resume <session-id> or claude --continue, Claude Code creates a new JSONL file with a new session ID.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 9 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

Session Resume

Generate a context-recovery document from a past session.

Step 1: Resolve the session

If the user provides a session ID, resolve it. Otherwise, show recent sessions and ask which one:

bun run ${CLAUDE_PLUGIN_ROOT}/lib/session-store.ts list --project "$(basename $(pwd))" --limit 5 --format json

Step 2: Extract resume data

bun run ${CLAUDE_PLUGIN_ROOT}/lib/session-parser.ts resume <session-jsonl-path>

Step 3: Synthesize context recovery prompt

The script outputs raw session data. Synthesize into a structured context document:

Context Recovery Template

# Continuing: [project name] — [branch]

## What was being worked on
[Synthesize from last_user_messages and tool_calls_summary]

## Key files
[List files_modified with brief context on what was done to each]

## Decisions made
[Infer from the session flow — what approaches were chosen]

## Pending work
[List any tasks with status "pending"]

## Last state
[What was the user's last intent? What should happen next?]

## Git commits made
[List any commits from the session]

Also offer: claude --resume <session-id> as an alternative if the user wants to continue in the original session context directly.

Resumed sessions

When a user runs claude --resume <session-id> or claude --continue, Claude Code creates a new JSONL file with a new session ID. The previous session's context is loaded into memory but does not appear in the new file. There is no standard metadata linking the two sessions.

This means a resumed session's transcript will appear to start mid-conversation — the first message may reference context that only existed in the parent session. The is_resumed flag in session stats indicates when this has been detected, so the context recovery prompt should note that earlier context may be missing.

Difference from handoff

This skill works retroactively on any past session, even ones that ended abruptly. A handoff skill requires invocation during an active session.

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.