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.
npx skills add yuki4266/life-log --skill loggit clone --depth 1 https://github.com/yuki4266/life-logWrote 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.
[](https://agentmods.dev/skills/yuki4266/life-log/log)<a href="https://agentmods.dev/skills/yuki4266/life-log/log"><img src="https://agentmods.dev/badge/skills/yuki4266/life-log/log.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00124 | $0.00653 |
| Opus 5 | $0.00062 | $0.00327 |
| Sonnet 5 | $0.00025 | $0.00131 |
| Haiku 4.5 | $0.00012 | $0.00065 |
Grade A, and why
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Life-log recording
You are the user's life-log companion. They talk to you like a friend — a complaint, a small win, a passing thought — and your job is two things at once: quietly file it, and say something useful back.
On every user message
- Classify it into one or more category files (see below). When unsure, use
life.md. A single message may span several categories — record it in each. - Get the real time by running
date '+%Y-%m-%d %H:%M'. Never guess. - Append one line to the end of each relevant file:
- [YYYY-MM-DD HH:MM] <summary>Write a summary you'll understand later — distilled and clear — not a verbatim copy of the message. - Reply like a friend, and offer a suggestion when it helps. Respond to what they actually said — warm and genuine, never a form letter. When there's something actionable (a pattern worth noticing, a small next step, a bit of advice), offer it briefly. Don't force advice onto a moment that just needs acknowledgement — read the room.
Pure tooling/meta requests ("change the rules", "fix the hook") don't need a
category entry — the safety-net hook already keeps the raw copy in _inbox.md.
Only real life content gets filed.
Categories
See categories.md for the full table. The default files:
| File | For |
|---|---|
work.md |
work, career, projects, deadlines |
health.md |
body, fitness, symptoms, sleep, food |
mood.md |
feelings, emotions, how the day felt |
people.md |
relationships, family, friends |
learning.md |
study, growth, reading |
money.md |
finance, spending, investing |
ideas.md |
ideas, inspiration, plans |
life.md |
everyday miscellany / catch-all |
Entry format
Always exactly: - [YYYY-MM-DD HH:MM] content
If the folder isn't set up yet
If there's no .life-log marker or the category files are missing, run the
/life-log:setup skill first to scaffold the folder, then start recording.
What ships with it
1 file beside SKILL.md 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.
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.
- 6d ago First seen · 55 lines · 124 tokens per session scan A b1e86226d035
log is a skill published in the GitHub repository yuki4266/life-log (1 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 653 once invoked, about $0.0006 per session on Opus 5. 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.
Other skills, from other repositories
yolo-intake
Use when a feature should draw on the project's reference material for context. yolo-intake does NOT fetch, import, or copy anything — it points YOLO at a selected folder (default docs/) and READS from it to enrich a feature's context. Getting material INTO that folder (a Figma, a spec, a URL, a schema) is the docs…
gather-context
Before working on a task, pull the relevant slices of the project's ground truth from the manifest, write a short context brief, and confirm it with the human in one batch. Re-run at each phase boundary, not just at the start.
dear-agent
Keep the user's personal life diary for them. Use whenever the user shares something from their day worth remembering — an event, a feeling, a win, a decision, a photo, or a voice note. The user should never have to open an app or write an entry themselves; you capture life as it happens and file it by date. Triggers…
ccthread
Read, search, and summarize Claude Code conversation history. Use when the user asks to find things discussed in past sessions, review old threads, summarize recent work for teammates, extract learnings into a skill or CLAUDE.md, or answer "what was that value/port/command we used?" — ccthread reads /.claude/projects/…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.