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 reviewgit 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/review)<a href="https://agentmods.dev/skills/yuki4266/life-log/review"><img src="https://agentmods.dev/badge/skills/yuki4266/life-log/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yuki4266/life-log/review"><img src="https://agentmods.dev/badge/skills/yuki4266/life-log/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.00714 |
| Opus 5 | $0.00036 | $0.00357 |
| Sonnet 5 | $0.00014 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
review 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 10d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Life-log review
Turn a month (or week) of scattered log lines into one reflective read-back: what happened, the patterns worth noticing, and a few concrete suggestions. This is the moment the log pays you back.
1. Determine the period
- Default: the current calendar month.
- Honor what the user asks: "review June", "this week", "last 30 days", a date
range. Compute the start/end dates with
dateso filtering is exact.
2. Gather the entries
Read each category file (work.md, health.md, mood.md, people.md,
learning.md, money.md, ideas.md, life.md, plus any custom ones). Keep
only lines whose [YYYY-MM-DD HH:MM] timestamp falls inside the period. If a
category has no entries in range, skip it.
3. Analyze from multiple perspectives
Give each domain its own focused lens. Prefer running these in parallel with
the Task tool — one subagent per non-empty category — so a rich review comes
back fast; fall back to analyzing them yourself in sequence if subagents aren't
available. Each lens receives only that category's in-range entries and returns:
- Summary — what actually happened this period, in 2-4 sentences.
- Patterns & trends — recurring themes, direction of travel (better/worse), anything cyclical (e.g. mood dips on certain days, spending creep).
- Flags — anything that deserves attention or care.
- Suggestions — 1-3 concrete, kind, actionable next steps for this domain.
For health/mood especially: be supportive and non-judgmental, never clinical or alarmist; suggest seeing a professional only if something genuinely warrants it.
4. Synthesize
Combine the lenses into one review. Look for cross-domain connections the per-lens agents couldn't see (e.g. rough moods clustering with work stress; spend spikes on low-sleep weeks). Then write:
- The month in a paragraph — a warm, honest read-back.
- Highlights & wins — don't only surface problems.
- Patterns worth noticing — the 2-4 that matter most, cross-domain.
- Suggestions — a short prioritized list (3-6), concrete and doable.
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.
- 10d ago First seen · 65 lines · 71 tokens per session scan A faf1d1fbc806
review is a skill published in the GitHub repository yuki4266/life-log (1 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 714 once invoked, about $0.0004 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
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
recipe-add-integration-tests
Add integration/E2E tests to existing codebase using Design Docs.
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.