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 localintelligencegit 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/localintelligence)<a href="https://agentmods.dev/skills/danielmiessler/lifeos/localintelligence"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/localintelligence/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/localintelligence"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/localintelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 24 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 45 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Output Handling · line 172 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00126 | $0.03213 |
| Opus 5.5 | $0.00050 | $0.01285 |
| Sonnet 5.5 | $0.00025 | $0.00643 |
| Haiku 4.5 | $0.00013 | $0.00321 |
Grade A, and why
LocalIntelligence scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://localhost:31337/notify \ How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LocalIntelligence
Customization
Before executing, check for user customizations at:
~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/LocalIntelligence/
If this directory exists, load and apply any PREFERENCES.md, optional source-list overrides, or per-source API keys (e.g., OpenStates, Google News topic ID). These override defaults. If the directory does not exist, proceed with skill defaults — universal sources only.
sources.json in the same directory is the deterministic per-city source list (RSS feeds, local JSON APIs) consumed by Tools/UserSources.ts on every refresh — see Tools/UserSources.help.md for the schema. City-specific URLs belong there, never in this skill.
Voice Notification
When executing a workflow, do BOTH:
-
Send voice notification:
curl -s -X POST http://localhost:31337/notify \ -H "Content-Type: application/json" \ -d '{"message": "Running WORKFLOWNAME in LocalIntelligence"}' \ > /dev/null 2>&1 & -
Output text notification:
Running **WorkflowName** in **LocalIntelligence**...
What It Does
LocalIntelligence is a civic intelligence aggregator for any US city. It pulls eight categories of local data — construction permits, crime, new businesses, public officials, legislation, elections, arrests, and local news — into a single daily JSON digest, keyed off the city in the principal's identity file and served to the Pulse LOCAL tab. Crime delegates to the dedicated crime-stats skill.
The Problem
What's actually happening where you live is scattered across a dozen sites that nobody checks — the city's permit portal, the council agenda system, the sheriff's blotter, a local paper, the elections office. No single feed tells you a new ordinance is up for a vote, a building is going up down the street, or an election is coming. Most "local news" tools either cover one city, hardcode endpoints that break, or paywall the good stories. This skill stays generic across every US city, resolves the target city at runtime, and degrades gracefully when a source has no data instead of blanking the whole digest.
What ships with it
26 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.
- References/DataSources.md 3.0 KB
- Tools/Backfill.ts 6.3 KB runs code
- Tools/ClaudeFill.help.md 1.0 KB
- Tools/ClaudeFill.ts 7.4 KB runs code
- Tools/FetchArrests.ts 803 B runs code
- Tools/FetchBusiness.ts 826 B runs code
- Tools/FetchConstruction.ts 1.0 KB runs code
- Tools/FetchCrime.ts 1.1 KB runs code
- Tools/FetchElections.ts 754 B runs code
- Tools/FetchLegislation.ts 872 B runs code
- Tools/FetchNews.ts 2.2 KB runs code
- Tools/FetchOfficials.ts 765 B runs code
- Tools/Hometown.ts 4.7 KB runs code
- Tools/Refresh.ts 6.5 KB runs code
- Tools/Types.ts 1.4 KB runs code
- Tools/UserSources.help.md 1.2 KB
- Tools/UserSources.ts 9.9 KB runs code
- Workflows/Arrests.md 1009 B
- Workflows/Business.md 814 B
- Workflows/Construction.md 1017 B
- Workflows/Crime.md 1.1 KB
- Workflows/DailyBrief.md 1.5 KB
- Workflows/Elections.md 800 B
- Workflows/Legislation.md 963 B
- Workflows/News.md 761 B
- Workflows/Officials.md 793 B
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.
- 1mo ago First seen · 195 lines · 126 tokens per session scan A a7bd4f7dc670
LocalIntelligence is a skill published in the GitHub repository danielmiessler/LifeOS (19,573 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 3,213 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
long-running-work
Carrying complex coding and project work through commands that take minutes or hours: evals, benchmarks, full builds and test suites, migrations, servers, multi-round runs. Use when a command may run past a few minutes, timed out once, or when the task spans several rounds of run, read results, fix, run again.
i-have-adhd
Action-first, zero-filler replies for a reader who loses the thread in prose. Use when the user asks for terse or direct answers, says too long, get to the point, tldr, stop rambling, or when replies keep getting cut off or ignored.
shortcuts
Run Apple Shortcuts on this Mac: list the available shortcuts first, then run one by exact name with optional input. Use when the user wants to trigger a shortcut or asks what shortcuts exist.
plan-devex-review
Interactive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to…
plan-tune
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and…
aster-capabilities
The complete map of what Aster can do and the exact command, flag, slash command, key, or config for each: install and sign-in, the chat TUI, permission modes and rules, every agent tool, review and fix, sessions, memory, config/keys/provider/model, mom.yaml routing, skills, plugins, MCP, web tools, sub-agents and…