Skip to content
Back to skills

Get History

ASecurity

Use when running on Claude Code and you need to examine past conversation, session logs, or raw chat history.

  • 101 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added February 7, 2026
developmentgobash

Works with

  • claude code
  • cli

Security analysis

A100/100

Scanned September 6, 2026

npx -y skills add cowwoc/cat --skill get-history --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Get History?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Get History
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cowwoc-get-history/badge)](https://www.skillsdirectory.com/skills/cowwoc-get-history)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
description: Use when running on Claude Code and you need to examine past conversation, session logs, or raw chat history.
allowed-tools: [Bash]
---

Resolve the installed `get-history` at `${CAT_PLUGIN_ROOT}/client/bin/get-history`. Pass the
session ID whose history you need as its first argument. Without `--agent`, the launcher selects that session's main
transcript. With `--agent <agent-id>`, it selects that subagent's transcript within the requested session. If the
launcher does not exist, report that exact path before applying the shared source-checkout fallback. Do not derive or
select a transcript path in Bash.

For example:

```bash
/absolute/path/get-history "$CLAUDE_CODE_SESSION_ID" analyze
/absolute/path/get-history "$CLAUDE_CODE_SESSION_ID" summary --since "2026-08-18T10:00:00Z" --type "message" --limit 50
/absolute/path/get-history "$CLAUDE_CODE_SESSION_ID" --agent "agent-123" search "keyword" --context 2
/absolute/path/get-history "$CLAUDE_CODE_SESSION_ID" errors
/absolute/path/get-history "$CLAUDE_CODE_SESSION_ID" file-history "config.json"
```

# Shared First Use

## Design Goals

- Ensure an agent reads and follows a selected skill's complete instructions once in each conversation context.

## Guidance

If you have not already read this skill's `first-use.md` in the current
conversation context, read it now and follow it exactly. Otherwise, reuse its guidance.
Read `first-use.md` again after the context resets or is compacted.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…