LifeOS is an AI-assisted personal operating system that records a person’s goals, values, context, and current situation to help move them toward a desired future state. It supports work such as building applications, starting businesses, and creative projects. Its catalogue entries extend the system through skills, hooks, agents, and commands.
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 danielmiessler/LifeOS --skill cardbenefitsgit clone --depth 1 https://github.com/danielmiessler/LifeOSWrote 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/danielmiessler/lifeos/cardbenefits)<a href="https://agentmods.dev/skills/danielmiessler/lifeos/cardbenefits"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/cardbenefits/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/danielmiessler/lifeos/cardbenefits"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/cardbenefits.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 | $0.00137 | $0.01420 |
| Opus 5.5 | $0.00055 | $0.00568 |
| Sonnet 5.5 | $0.00027 | $0.00284 |
| Haiku 4.5 | $0.00014 | $0.00142 |
Grade A, and why
CardBenefits 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CardBenefits
Single source of truth for the principal's credit cards, their perks and points balances, and the planning layer that turns points into trips.
Ideal State
- Every perk, credit or balance in an answer comes from the USER data files read in that run, and anything stale (>90 days) or marked UNVERIFIED is flagged inline instead of stated as fact.
- Each recommendation names the card, program or credit, its dollar or points value, and the exact next step the principal takes.
- The data files stay the single source of truth: balances change only on the principal's report or a statement, perks only after a web-verified refresh, credit status only on confirmed usage.
- Money never moves from this skill: transfers, bookings and activations are planned here. Where a booking skill is installed, it carries out a plan only after the principal's yes on the itemized total; otherwise the principal executes.
Intent Routing
| Intent | Trigger | File |
|---|---|---|
| ShowBenefits | "what perks do I have", "card benefits", "which card for X" | Intents/ShowBenefits.md |
| UpdatePoints | "I have N points", "update my points", "new balance" | Intents/UpdatePoints.md |
| PlanRedemption | "plan a trip with points", "use my points for", "what can N points get" | Intents/PlanRedemption.md |
| RefreshPerks | "refresh perks", "did the benefits change", "verify card benefits" | Intents/RefreshPerks.md |
| CreditSweep | "unused credits", "credits on the table", "expiring credits", "monthly credit check" | Intents/CreditSweep.md |
| File | Read when |
|---|---|
Setup.md |
first-time setup of the four data files, with an invented worked example of each and a proof command |
Data & Config
This skill is procedure only. All personal financial data (card inventory, balances, credits, cross-card strategy, standing travel preferences) lives in the USER tree at <configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/CardBenefits/ and is read by path on every invocation (configRoot is $CLAUDE_CONFIG_DIR when set, else ~/.claude). First-time setup, a worked example of each file and a proof command: Setup.md. When Cards.md is missing, stop and point the principal at Setup.md; never answer perks from model memory.
What ships with it
6 files 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.
- 10d ago First seen · 81 lines · 137 tokens per session scan A 87708d2f39c2
CardBenefits is a skill published in the GitHub repository danielmiessler/LifeOS (19,717 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 1,420 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-28.
CardBenefits compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| CardBenefitsdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 137 | Claude Code, Codex |
| company-cfocoreyhaines31/makerskills | Skill | 890 | yesterday | MIT | A | 202 | Claude Code |
| personal-cfocoreyhaines31/makerskills | Skill | 890 | yesterday | MIT | A | 209 | Claude Code |
| kyc-escalationmohitagw15856/pm-claude-skills | Skill | 1.5k | yesterday | MIT | A | 93 | Claude Code |
| ai-roi-auditmohitagw15856/pm-claude-skills | Skill | 1.5k | yesterday | MIT | A | 118 | Claude Code |
| credit-memomohitagw15856/pm-claude-skills | Skill | 1.5k | yesterday | MIT | A | 83 | Claude Code |
| loan-covenant-reviewmohitagw15856/pm-claude-skills | Skill | 1.5k | yesterday | MIT | A | 95 | Claude Code |