Claude Code mod

agent-journal

A journal written by your agent, autonomously. One small markdown file per milestone, written as the work happens, in a format built to be scanned with grep and ls.

8 starsMemory & instructions modsValidates on Claude Code 2.1.326 Source

Install

From source
git clone https://github.com/zirkelc/agent-journal.git
claude --plugin-dir ./agent-journal/claude-code

The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.

What it can access

Reach
L2Writes or runs: runs processes, drives Claude, writes the prompt box, reads files, reads env vars, reads the transcript, reads mod state, persists state, draws
Sees
the system prompt, compaction, every prompt, /"^mcp__agent-journal__write$"/ calls, /"^mcp__agent-journal__(list|read)$"/ calls, Write calls
Draws in
ToolUseToolResultPane
Hooks
session.startprompt.contextsession.compactprompt.submitturn.startagent.offertool.describetool.callui.rendercommand.runturn.completesession.endui.pressui.inputui.closeui.scroll

From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs

Details

Folder
claude-code
Author
Chris Cook
License
MIT
Last updated
13 November 2026

FAQ

What is agent-journal?

A journal written by your agent, autonomously. One small markdown file per milestone, written as the work happens, in a format built to be scanned with grep and ls. It is a mod for Claude Code, from zirkelc/agent-journal on GitHub.

What can the agent-journal mod access?

Its widest reach is "writes or runs" (runs processes, drives Claude, writes the prompt box, reads files, reads env vars, reads the transcript, reads mod state, persists state, draws). It sees the system prompt, compaction, every prompt, /"^mcp__agent-journal__write$"/ calls, /"^mcp__agent-journal__(list|read)$"/ calls, Write calls. It draws in ToolUse, ToolResult, Pane. Like any mod, it runs with your permissions.

How do I install agent-journal?

Clone zirkelc/agent-journal and start Claude Code with --plugin-dir pointing at the mod's folder (claude-code).

Is agent-journal popular?

zirkelc/agent-journal has 8 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 13 November 2026.

More memory & instructions mods

Browse the most popular Claude Code mods, all memory & instructions mods, or the skills and MCP server directories.