life-log

life-log is a plugin for Claude Code from yuki4266/life-log. Its manifest loads nothing; the 3 skills, 1 hook it bundles cost 300 tokens per session together, scanned A, original, MIT.

A local journaling tool for Claude Code that sorts messages into dated Markdown notes by category and offers a suggestion afterward.

In plain words
What is it for?
Recording complaints, quick notes, and diary entries as entries in categories such as work, health, mood, people, learning, money, ideas, and life.
Why use it?
It reduces the effort of filing everyday thoughts and keeps the notes on your own computer rather than in a cloud service.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add yuki4266/life-log
agentmods
npx agentmods add plugins/yuki4266/life-log/life-log
Clone the repo
git clone --depth 1 https://github.com/yuki4266/life-log

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for life-log

README.md
[![agentmods](https://agentmods.dev/badge/plugins/yuki4266/life-log/life-log.svg)](https://agentmods.dev/plugins/yuki4266/life-log/life-log)
Your own site
<a href="https://agentmods.dev/plugins/yuki4266/life-log/life-log"><img src="https://agentmods.dev/badge/plugins/yuki4266/life-log/life-log.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 3 skills, 1 hook cost 300 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

life-log scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "life-log",
  "description": "Talk to Claude Code like a friend — a complaint or a quick note — and it auto-classifies, timestamps, and files each message into dated category notes, then gives you a suggestion. A UserPromptSubmit safety-net hook means nothing you say is ever lost. Local-first, plain markdown, no cloud.",
  "version": "0.1.0",
  "author": {
    "name": "yuki4266",
    "url": "https://github.com/yuki4266"
  },
  "homepage": "https://github.com/yuki4266/life-log",
  "repository": "https://github.com/yuki4266/life-log",
  "license": "MIT",
  "keywords": [
    "journaling",
    "life-log",
    "diary",
    "productivity",
    "local-first",
    "markdown",
    "companion"
  ]
}
Contents

What it installs

The manifest is a name and a version. 3 skills, 1 hook travel with it, and installing the plugin installs all of them — 300 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 22 lines scan A 2d4008fb016b

Subscribe to this mod's changes

life-log is a plugin published in the GitHub repository yuki4266/life-log (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other plugins, from other repositories

prime-context

Self-learning project context — bare /prime-context captures the session's learnings into area context files; /prime-context loads context on demand; thin AGENTS.md router, structure audit (doctor), drift warnings at session start.

rodrigopg/claude-skill-prime-context · not measured

obsidian-chronicle

Auto-records Claude Code sessions as structured Obsidian notes + Daily Note entries (via the SessionEnd/PreCompact hooks and /done), and ships the obsidian-vault agent — the unified handler for all Obsidian vault work (create, edit, search, organize notes, tasks, canvases, bases). Configure with…

takashito/claude-obsidian-chronicle · not measured

ccthread

Read, search, and summarize Claude Code conversation logs from /.claude/projects.

jakemarsh/ccthread · not measured

recall

Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.

raiyanyahya/recall · not measured

toonify-mcp

Local context compression for Claude Code workflows, including structured data and debug-heavy output.

PCIRCLE-AI/toonify-mcp · not measured

axme-code

(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.

AxmeAI/axme-code · not measured