agentleFS
Sign inStart free
AndytoizerAndytoizer/session-history/CLAUDE.md

session-history

CLAUDE.md1 starsChanged 6 months agoMITView on GitHub

This repository packages the session-history skill and CLI. The tool scans local Claude Code and Codex JSONL transcripts, infers project/thread groupings, and writes a browsable Markdown library. For test fixtures, use --codex-root, --claude-root, and --output against temporary directories so real transcripts are not copied into the repository.

The file

We split this CLAUDE.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Do not commit generated transcript libraries, raw user transcripts, or ~/.session-history output.

    line 9
  2. Distinctive:

    Keep the public package free of personal paths, customer names, private project taxonomies, API keys, and secrets.

    line 10
  3. Distinctive:

    Prefer portable defaults and configurable roots over hard-coded user-specific paths.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

CLAUDE.md

Project

This repository packages the session-history skill and CLI. The tool scans local Claude Code and Codex JSONL transcripts, infers project/thread groupings, and writes a browsable Markdown library.

Guardrails

  • Do not commit generated transcript libraries, raw user transcripts, or ~/.session-history output.
  • Keep the public package free of personal paths, customer names, private project taxonomies, API keys, and secrets.
  • Prefer portable defaults and configurable roots over hard-coded user-specific paths.
  • The script should remain standard-library only unless there is a strong reason to add dependencies.

Useful Commands

python3 scripts/session_history.py menu
python3 scripts/session_history.py find "search terms"
python3 -m py_compile scripts/session_history.py

For test fixtures, use --codex-root, --claude-root, and --output against temporary directories so real transcripts are not copied into the repository.

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.

Check your setup, free