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 agentmods add instructions/jasonhnd/life_os/agents-mdgit clone --depth 1 https://github.com/jasonhnd/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/instructions/jasonhnd/life_os/agents-md)<a href="https://agentmods.dev/instructions/jasonhnd/life_os/agents-md"><img src="https://agentmods.dev/badge/instructions/jasonhnd/life_os/agents-md.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 | $0.00670 | $0.00670 |
| Opus 5 | $0.00335 | $0.00335 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
life_OS AGENTS.md 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Life OS · Repository Guidance
SKILL.md is the sole universal runtime authority for Life OS.
This file guides contributors and coding agents working in the Life OS source repository. It does not define an additional user-facing workflow.
Repository Scope
- Treat the current Life OS checkout as the default development boundary.
- Do not inspect, read, validate, migrate, or modify a user's second-brain unless the user explicitly places that directory in scope.
- Do not infer second-brain access from passive screen context, nearby paths, Git configuration, or prior sessions.
- Preserve unrelated worktree changes.
- Keep historical material as history unless the task explicitly includes archival cleanup.
Authority and Layers
| Layer | Responsibility |
|---|---|
SKILL.md |
Universal runtime purpose, boundaries, and completion standard |
hosts/*.md |
Host capabilities and adaptation notes |
agents/*.md |
Optional reusable role templates |
themes/*.md |
Optional presentation adapters |
references/*.md |
Non-authoritative data and pattern references |
evals/ |
Outcome-based conformance scenarios |
docs/history/ |
Superseded architecture and release evidence |
No host, agent, reference, command, or test document may override
SKILL.md.
Development Principles
- Implement the requested outcome rather than a ceremonial process.
- Use available tools, including Shell and CLI, when they are useful.
- Do not add a script, command, runner, hook, daemon, CI job, or fixed agent chain as a hidden runtime prerequisite.
- Existing agents are optional templates. Use no subagent when direct work is sufficient; create a task-specific subagent when it materially helps and the host supports it.
- Ask the user only for material ambiguity, scope expansion, or missing authority.
- Make the smallest coherent change that leaves active documentation and behavior consistent.
File Changes
- Use scoped, reviewable edits.
- Do not rewrite user data to test a migration; use repository-local synthetic fixtures.
- Do not introduce a second universal specification beside
SKILL.md. - When retiring an old contract, either move it under
docs/history/or mark it clearly non-authoritative and remove active references. - Update directly affected current documentation and conformance scenarios.
- Preserve valid historical records rather than rewriting earlier releases to look current.
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.
- 4d ago First seen · 84 lines · 670 tokens per session scan A 5107899718f9
life_OS AGENTS.md is an instructions file published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 27d ago), licensed Apache-2.0. It adds 670 tokens to every session, about $0.0034 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 instructions, from other repositories
council-of-high-intelligence CLAUDE.md
Claude Code instructions for 0xNyk/council-of-high-intelligence, covering council of high intelligence, architecture, conventions, agent files and skill.md.
cc-thinking-skills CLAUDE.md
Instructions for tjboudreaux/cc-thinking-skills: Follow AGENTS.md for repository workflow.
detroit-ai-player AGENTS.md
Instructions for Baba88611/detroit-ai-player, covering agents.md — 给 ai agent 的部署与运行指引, 这是什么, 前置检查, 装依赖 and 选后端（决策树，按顺序判断）.
foreman CLAUDE.md
Instructions for fatihguner/foreman, covering foreman — project context, architecture overview, system layers, core content layers and orchestration layers.
lifeos-template CLAUDE.md
Claude Code instructions for seandavi/lifeos-template, covering claude.md — operating manifest for this vault, preferences, philosophy, co-thinking mode and file layout.
archsight-cognition GEMINI.md
Instructions for ArchSightLabs/archsight-cognition, covering gemini.md, 必读入口 and gemini 特别说明.