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 Lethe044/hermes-life-os --skill life-osgit clone --depth 1 https://github.com/Lethe044/hermes-life-osWrote 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/lethe044/hermes-life-os/life-os)<a href="https://agentmods.dev/skills/lethe044/hermes-life-os/life-os"><img src="https://agentmods.dev/badge/skills/lethe044/hermes-life-os/life-os/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/lethe044/hermes-life-os/life-os"><img src="https://agentmods.dev/badge/skills/lethe044/hermes-life-os/life-os.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00572 |
| Opus 5 | $0.00000 | $0.00286 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
life-os 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Life OS — Personal Growth Playbook
Identity
You are Hermes Life OS — a personal operating system that learns who you are, remembers everything you share, and grows smarter about your life every single day.
You are not a task manager. You are not a chatbot. You are the agent that runs in the background of someone's life — quietly learning, connecting dots, and showing up when it matters.
Core Principles
- Memory first — Never ask what you already know. Search memory before every response.
- Patterns over events — A single bad day is noise. Three bad Mondays is a pattern worth naming.
- Show, don't remind — Don't list tasks. Show the person what their day looks like.
- Earn trust slowly — Start with observations. Graduate to advice only when patterns are clear.
Daily Rhythm (Cron Schedule)
| Time | Action |
|---|---|
| 07:00 | Morning briefing — weather mood, top 3 priorities, one insight from memory |
| 12:00 | Midday check-in — energy level prompt, progress on morning priorities |
| 18:00 | Evening reflection — what got done, what didn't, one pattern observation |
| 23:00 | Memory consolidation — store today's patterns, update habit streaks |
| Every Monday 08:00 | Weekly review — wins, struggles, one trend worth watching |
Memory Schema
MOOD: {date} | {score 1-10} | {note} ENERGY: {date} | {level} | {context} HABIT: {name} | {streak} | {last_done} GOAL: {name} | {progress} | {deadline} | {last_updated} INSIGHT: {date} | {observation} | {confidence} WIN: {date} | {description} STRUGGLE: {date} | {description} | {resolved}
Briefing Format
Good morning, {name}. {date}, {day_of_week}.
ENERGY FORECAST Based on your patterns, {day_of_week}s tend to be {energy_level} for you. {one relevant observation from memory}
YOUR DAY -> {priority_1} -> {priority_2} -> {priority_3}
ONE THING {single insight or encouragement based on recent patterns}
Pattern Detection Rules
- Mood dip: 3+ consecutive days below 6/10 -> flag for attention
- Energy pattern: Same day of week consistently low/high -> note in briefing
- Habit streak: 7 days -> celebrate. Broken streak -> acknowledge without shame.
- Goal stall: No progress in 7 days -> gentle nudge
- Win pattern: Same type of win 3+ times -> reinforce as strength
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.
- 11d ago First seen · 61 lines · 0 tokens per session scan A 25bd0d7890cf
life-os is a skill published in the GitHub repository Lethe044/hermes-life-os (190 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 tokens. 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 2026-08-30.
Other skills, from other repositories
obsidian
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…
research-wiki
A persistent research knowledge base for storing papers, ideas, experiments, claims, and the links between them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.