herdr
Operate the Herdr terminal multiplexer (0.9.x): named sessions, workspaces/tabs/panes, agent states, hooks, socket API, restart and husk behavior, and the…
Skill by 8-BitRhyon
Chalk Labs
Need help deploying herdr?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/8-bitrhyon-herdr
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/herdr
What's inside
- Skill name
herdr- Description
- Operate the Herdr terminal multiplexer (0.9.x): named sessions, workspaces/tabs/panes, agent states, hooks, socket API, restart and husk behavior, and the captain-crew pattern. Load when running or supervising multiple agents in one workspace.
- License
- MIT
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Herdr Multiplexing > Herdr is an agent-aware terminal multiplexer. It keeps real panes alive and classifies each agent as `working`, `blocked`, `done`, `idle`, or `unknown`. Requires: `herdr` 0.9+ on PATH. The installed binary is authoritative: run `herdr <command> --help`. ## Concepts - **Session:** one server per session. Pass `--session <name>` or set `HERDR_SESSION`. - **Workspace -> tab -> pane:** IDs are session-scoped (`w3`, `w3:t1`, `w3:p1`). Re-read them after close, split, or restart. - **State:** a registration is a hint. Confirm with `pane process-info` before trusting or relaunching. - **Daemon:** detaching or losing SSH does not kill panes. `server stop` does, and it kills every pane. ## Environment And Nesting Panes get `HERDR_ENV=1`, `HERDR_PANE_ID`, `HERDR_SESSION`, and `HERDR_SOCKET_PATH`. A tmux started inside a Herdr pane sets `$TMUX` for its children. Backend detection that checks `$TMUX` first then hides the agent. Guard shell auto-start with `[[ -z "$HERDR_ENV" ]]`. Never start tmux inside a Herdr pane. ## CLI ``` herdr status [--json] [--session <name>] herdr session list [--json] herdr workspace list|get|create --cwd <path> [--label] [--no-focus]|focus|rename|close herdr tab list|create --workspace <id> [--label]|get|focus|rename|close herdr pane list|get|current|process-info|read <id> [--lines N] [--format text|ansi] herdr pane run <id> "<command>" herdr pane send-text|send-keys <id> <text|Enter|Escape|C-c> herdr pane split <id> --direction right|down [--no-focus]|focus|rename|close herdr agent list|get <id>|explain <id>|attach <id> herdr agent prompt <id> "<task>" [--wait [--until done] [--timeout MS]] herdr agent wait <id> --until done [--until blocked ...] herdr terminal attach <terminal_id> herdr integration install <pi|claude|codex|opencode|kilo|...> herdr integration status herdr api snapshot|schema ``` ## Integrations `herdr integration install <agent>` installs a native state hook. `integration status` lists what is installed. Focus Notify toasts on block or finish. ## Restart And Husks - A restart preserves layout IDs, not harness processes or registrations. - A restored tab with no live agent is a husk. `agent get` can show a stale registration. - Confirm with `pane process-info`: a foreground of only shells means the agent is gone. Relaunch it. - Do not replace a tab before the old pane is confirmed dead; the last tab can take its workspace with it. - Restarting the daemon kills every pane. Get consent first. ## Captain Pattern 1. Decompose into independent units (`task-decomposition`). 2. Give each worker a clean worktree (`git-worktree`). 3. Keep the captain free: delegate by default, escalate only decisions. 4. Watch `agent list` and `pane read`; steer blocked workers before killing them. 5. Return worktrees and close panes when done. ## Verification - `pane list` and `agent list` show the expected topology and states. - `pane process-info` proves the harness is live. - `agent explain <id>` explains a wrong state. - `integration status` shows the hook installed. ## Invocation Load when supervising multiple agents, spawning or splitting panes, or running the captain pattern.
From 8-BitRhyon/monozen-skills, MIT.
More from 8-BitRhyon/monozen-skills
- 0.567score
asd-ste100
8-BitRhyon
Enforce ASD-STE100 (Simplified Technical English) specification rules for all technical documentation, Markdown files, and code comments with zero em dashes.
SkillAFreshness: AClaude Code +9 - 0.565score
backpass
8-BitRhyon
Gradient descent for agent memory and instructions.
SkillAFreshness: AClaude Code +9 - 0.565score
production-web-audit
8-BitRhyon
Universal pre-deployment and release audit protocol for web applications: covers security headers & CSP, event/memory leak prevention, accessibility &…
SkillAFreshness: AClaude Code +9 - 0.561score
firstmate
8-BitRhyon
Captain-and-crew orchestration distro: Captain, First Mate, Second Mates, and Crewmates; lifecycle (/ahoy, /bearings), backend selection (Herdr, tmux, Rex…
SkillAFreshness: AClaude Code +9 - 0.561score
pr-workflow
8-BitRhyon
Universal pull request lifecycle for any GitHub repo: branch strategy, PR creation, CI checks, review gate, merge (including protected branches), and cleanup.
SkillAFreshness: AClaude Code +9 - 0.561score
no-mistakes
8-BitRhyon
Run automated AI-driven validation pipelines and zero-slop PR creation through the no-mistakes local git proxy gate.
SkillAFreshness: AClaude Code +9 - 0.561score
axi
8-BitRhyon
Build and use agent-ergonomic CLI wrappers (AXI style) instead of MCP: TOON output, minimal schemas, truncation hints, total counts, empty states, structured…
SkillAFreshness: AClaude Code +9 - 0.539score
grilling
8-BitRhyon
Grill the user relentlessly about a plan, decision, or idea.
SkillAFreshness: AClaude Code +9 - 0.529score
llm-as-verifier
8-BitRhyon
Verification framework from the Stanford + NVIDIA LLM-as-a-Verifier paper (arXiv:2607.05391): continuous scores from expectation over scoring-token logits…
SkillBFreshness: BClaude Code +9 - 0.525score
grill-me
8-BitRhyon
A relentless interview to sharpen a plan or design.
SkillAFreshness: AClaude Code +9 - 0.521score
prompt-engineering-loop
8-BitRhyon
Lean iterative prompt refinement protocol - ELI10 structuring, clarifying questions, working examples, adversarial pressure testing, and verification-ladder…
SkillBFreshness: BClaude Code +9 - 0.521score
code-review
8-BitRhyon
Universal code review protocol for any language and any repository: five review dimensions (correctness, readability, architecture, security, performance)…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/8-BitRhyon/monozen-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 8-BitRhyon
- 0.567score
asd-ste100
8-BitRhyon
Enforce ASD-STE100 (Simplified Technical English) specification rules for all technical documentation, Markdown files, and code comments with zero em dashes.
SkillAFreshness: AClaude Code +9 - 0.565score
backpass
8-BitRhyon
Gradient descent for agent memory and instructions.
SkillAFreshness: AClaude Code +9 - 0.565score
production-web-audit
8-BitRhyon
Universal pre-deployment and release audit protocol for web applications: covers security headers & CSP, event/memory leak prevention, accessibility &…
SkillAFreshness: AClaude Code +9 - 0.561score
no-mistakes
8-BitRhyon
Run automated AI-driven validation pipelines and zero-slop PR creation through the no-mistakes local git proxy gate.
SkillAFreshness: AClaude Code +9 - 0.561score
axi
8-BitRhyon
Build and use agent-ergonomic CLI wrappers (AXI style) instead of MCP: TOON output, minimal schemas, truncation hints, total counts, empty states, structured…
SkillAFreshness: AClaude Code +9 - 0.561score
firstmate
8-BitRhyon
Captain-and-crew orchestration distro: Captain, First Mate, Second Mates, and Crewmates; lifecycle (/ahoy, /bearings), backend selection (Herdr, tmux, Rex…
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get herdr running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
herdr skill. Agent Mart. https://agentmart.dev/skills/8-bitrhyon-herdr (last updated 2026-10-24)