AnnualReports
Aggregate several hundred cybersecurity annual reports from CrowdStrike, Mandiant, IBM, Verizon, Microsoft, CISA, OWASP, Wiz,…
Operates herdr, the terminal workspace manager for coding agents, through its CLI and socket API, explains and edits the local herdr setup (config.toml key mirror, shell wrapper, terminal passthrough maps, sidebar naming, agent-state integrations), and checks the install against
Claude Code
$ npx -y skills add danielmiessler/lifeos --skill Herdr --agent claude-code
Codex
$ npx skills add danielmiessler/lifeos --skill Herdr -a codex -y
Cursor
$ npx skills add danielmiessler/lifeos --skill Herdr -a cursor -y
Gemini CLI
$ npx skills add danielmiessler/lifeos --skill Herdr -a gemini-cli -y
GitHub Copilot
$ npx skills add danielmiessler/lifeos --skill Herdr -a github-copilot -y
OpenCode
$ npx skills add danielmiessler/lifeos --skill Herdr -a opencode -y
Windsurf
$ npx skills add danielmiessler/lifeos --skill Herdr -a windsurf -y
name: Herdr
metadata:
short-description: "Operates the herdr terminal workspace manager for coding agents, explains and edits the local herdr setup, and checks it against upstream."
version: 1.1.1
description: Operates herdr, the terminal workspace manager for coding agents, through its CLI and socket API, explains and edits the local herdr setup (config.toml key mirror, shell wrapper, terminal passthrough maps, sidebar naming, agent-state integrations), and checks the install against upstream. USE WHEN herdr, herder, herd, herdr command, herdr pane, herdr tab, herdr workspace, herdr worktree, start an agent in a pane, prompt the agent in the other pane, read that pane, what are my other agents doing, herdr config, herdr keybinding, herdr sidebar, herdr integration, herdr docs, update herdr, is herdr up to date, herdr remote, herdr machine. NOT FOR in-harness subagents (Agent or Workflow), the Helm terminal itself outside herdr (Helm docs), the Hermes sidecar (Hermes).
evals:
deterministic:
- command: "bun skills/Herdr/Tools/Freshness.ts --json --offline"
falsifier: "exits 2 when herdr is not runnable, or exits 1 naming the check when a config key is unknown to the binary, an installed integration is not current, the server is stale, or herdr's own skill text changed since the accepted baseline"**Contents:** Ideal State · Intent Routing · Sources of Truth · This Install · Data & Config · Gotchas · Examples
Herdr documents itself for agents, so this skill holds no command syntax. It names where the syntax lives, what is custom about this install, and how to tell when either has drifted.
| Intent | Trigger | File | |----------|---------|------| | **Operate** | control panes, tabs, workspaces, worktrees; start, prompt, read or wait on an agent; "what are my other agents doing" | `Intents/Operate.md` | | **Delegate** | "have codex / another claude do X in a pane", "get a second opinion in a pane", spin up an agent next to me | `Intents/Delegate.md` | | **Configure** | keybindings, theme, sidebar, toasts, integrations, the wrapper or passthrough maps, "why does this key do that in herdr" | `Intents/Configure.md` | | **Freshness** | "is herdr up to date", docs drift, after any herdr update | `Intents/Freshness.md` | | **Update** | "update herdr", "upgrade herdr", a stale `version` or `server` check | `Intents/Update.md` |
| File | Read when | |------|-----------| | `Setup.md` | first-time setup: the freshness baseline files, environment variables, and the commands that prove the install works |
Read these at use time. The installed binary outranks the website when they disagree, because the site describes the newest release.
| Need | Source | |------|--------| | How an agent should drive herdr, with safety rules | `herdr --skill` | | Exact syntax for a command group | the group with no subcommand: `herdr agent`, `herdr pane`, `herdr tab`, `herdr workspace`, `herdr worktree`, `herdr terminal`, `herdr notification`, `herdr integration`, `herdr session`, `herdr machine` | | Socket API methods and shapes | `herdr api schema --json` | | Live state of the session | `herdr api snapshot`, `herdr agent list`, `herdr status` | | Every config key, its type and default | `herdr --default-config` for this binary; the config reference JSON linked from the docs index for prose | | Any doc page (plugins, remote, session restore, troubleshooting) | the index at `https://herdr.dev/llms.txt`, then only the page the task needs | | What changed in the newest release | `release-notes.json` beside `config.toml` |
The config reference is one large JSON file. Filter it by key:
curl -fsSL "<config reference URL from the index>" | jq --arg key 'ui.sidebar_width' '.sections[].keys[] | select(.key == $key)'
Optional: if `LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Herdr/ThisInstall.md` exists, read it for the local pieces around herdr (config mirror, shell wrapper, passthrough maps, sidebar naming, hooks); without it, rely on the sources above.
Freshness baseline and the last accepted copy of herdr's skill text: `LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Herdr/` (`freshness.json`, `upstream-skill.md`). The snapshot exists only so a changed skill can be diffed; it is never the instruction source. Both files are created by `Tools/Freshness.ts --accept`; with no baseline the `skill_hash` check reports stale and says to run it. First-time setup and the commands that prove the install: [Setup.md](Setup.md).
⛰️ LifeOS — The universal AI Harness designed to move you from Current to Ideal state in both life and work.
Aggregate several hundred cybersecurity annual reports from CrowdStrike, Mandiant, IBM, Verizon, Microsoft, CISA, OWASP, Wiz,…
3-pass scope oscillation that holds a question constant while shifting zoom — narrow/tactical, wide/strategic, then synthesis —…
Curated aphorism collection with CRUD: content-based matching, themed search, thinker research, and usage tracking to avoid…
Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses…
Static visual content in 20+ formats (diagrams, infographics, comics, icons, wallpaper) via Nano Banana Pro by default, Nano…
Directs visual quality across images, films, slides, and site captures through a direction council, two vendors' vision judgments…
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI…