herdr/SKILL.md
Control herdr from inside it. Manage workspaces and tabs, split panes, run commands, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1).
npx skillsauth add ninehills/skills herdrInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
you are running inside herdr, a terminal-native agent multiplexer. herdr gives you workspaces, tabs, and panes — each pane is a real terminal with its own shell, agent, server, or log stream — and you can control all of it from the cli.
this means you can:
the herdr binary is available in your PATH. its workspace, tab, pane, and wait commands talk to the running herdr instance over a local unix socket.
if you need the raw protocol or full api reference, read the socket api docs.
this skill documents herdr v0.5.8. commands were verified against the actual binary. do not assume newer features (like herdr agent subcommands) exist unless confirmed.
workspaces are project contexts. each workspace has one or more tabs. unless manually renamed, a workspace's label follows the first tab's root pane — usually the repo name, otherwise the root pane's current folder name.
tabs are subcontexts inside a workspace. each tab has one or more panes.
panes are terminal splits inside a tab. each pane runs its own process — a shell, an agent, a server, anything.
agent status is detected automatically by herdr. the api exposes one public field for it:
agent_status — idle, working, blocked, done, unknowndone means the agent finished, but you have not looked at that finished pane yet.
plain shells still exist as panes, but herdr's sidebar agent section intentionally focuses on detected agents rather than listing every shell.
ids — herdr v0.5.8 uses opaque workspace-scoped pane ids like w651d456f8444f3-2. tab ids look like w651d456f8444f3:2. workspace ids look like w651d456f8444f3. always re-read ids from herdr pane list before using them — do not hardcode or guess.
see what panes exist and which one is focused:
herdr pane list
the focused pane is yours (look for "focused": true). other panes are your neighbors.
list workspaces:
herdr workspace list
do not use shell redirection like > /tmp/output.txt or 2>&1 | tee /tmp/log when running commands in a herdr pane via herdr pane run. herdr's value is seeing the live terminal stream — the agent's own output, colours, formatting, and progress indicators. redirecting hides all of that and makes the pane appear frozen.
instead, observe output with:
herdr pane read <id> --source recent --lines N — read what is already in the scrollbackherdr wait output <id> --match "pattern" --timeout N — block until expected output appearsherdr pane read <id> --source visible --ansi — get an ANSI snapshot for TUI feedback loopsherdr v0.5.8 does not have herdr agent commands. all interaction goes through herdr pane:
herdr pane list — list all panes, find your pane id and neighborsherdr pane read <id> --source recent --lines N — read what is on the screenherdr pane send-text <id> "text" — send text without pressing enterherdr pane send-keys <id> Enter — press a key (Enter, CtrlC, Escape, etc.)herdr pane run <id> "command" — send text + enter atomicallyherdr pane split <id> --direction right|down [--no-focus] [--cwd PATH] — split and create a new paneherdr pane close <id> — close a paneherdr pane rename <id> "label"|--clear — assign or clear a pane labelherdr pane get <id> — get detailed info about a paneherdr pane run <id> "text" sends text + Enter atomically and returns immediately. it does not wait for the receiving side to process the message.
# send a complete message — runs "npm test" in the pane's shell
herdr pane run w651d456f8444f3-3 "npm test"
# send text to an agent in the pane
herdr pane run w651d456f8444f3-3 "review the test coverage in src/api/"
herdr pane send-text <id> "text" sends raw text without pressing enter. use herdr pane send-keys <id> Enter to press enter separately:
# send text without enter
herdr pane send-text w651d456f8444f3-3 "hello"
# press enter
herdr pane send-keys w651d456f8444f3-3 Enter
important: pane run appends \r (carriage return) to the text, equivalent to pressing enter. the command runs in the pane's existing shell process — it does not start a new shell. if the pane is at an agent prompt (e.g. > or the pi input line), the command text will be sent to the agent, not executed as a shell command.
there is no built-in delay or --wait flag on pane run or pane send-text. both return immediately. to pace messages to an agent, use herdr wait agent-status --status idle between sends:
# send a message
herdr pane run w651d456f8444f3-3 "review the test coverage"
# wait until the agent is idle again
herdr wait agent-status w651d456f8444f3-3 --status idle --timeout 120000
# now send the next message
herdr pane run w651d456f8444f3-3 "also check src/utils/"
split a new pane, then run the agent in it:
# split to the right without stealing focus
herdr pane split w651d456f8444f3-2 --direction right --no-focus
# parse the new pane id from the JSON response
# the response is: {"result":{"pane":{"pane_id":"w651d456f8444f3-6", ...}}, ...}
# run the agent in the new pane
herdr pane run w651d456f8444f3-6 "pi"
# wait for the agent prompt to appear (adjust match pattern for your agent)
herdr wait output w651d456f8444f3-6 --match "thinking" --timeout 30000
# give it a task
herdr pane run w651d456f8444f3-6 "review the test coverage in src/api/"
do not pipe the agent's output (e.g. pi | tee /tmp/log) when starting — the command text is sent to the pane's shell, not as a pipe target. let the agent's output flow naturally to the pane.
herdr wait output watches for text in a pane's terminal output. useful for servers, builds, logs:
herdr wait output w651d456f8444f3-3 --match "ready on port 3000" --timeout 30000
herdr wait output w651d456f8444f3-3 --match "test result" --timeout 60000
herdr wait output w651d456f8444f3-3 --match "server.*ready" --regex --timeout 30000
herdr wait agent-status watches for the agent status field on a pane. useful for coding agents:
herdr wait agent-status w651d456f8444f3-3 --status done --timeout 60000
herdr wait agent-status w651d456f8444f3-3 --status idle --timeout 60000
herdr wait agent-status w651d456f8444f3-3 --status blocked --timeout 300000
tip: wait output matches against unwrapped recent terminal text. pane width and soft wrapping do not break matches. if you want to inspect the same transcript that the waiter matched, use pane read --source recent-unwrapped.
both commands exit code 1 on timeout.
# current viewport (what is visible right now)
herdr pane read w651d456f8444f3-3 --source visible --lines 80
# recent scrollback (what was printed recently)
herdr pane read w651d456f8444f3-3 --source recent --lines 50
# without soft wrapping (best for logs)
herdr pane read w651d456f8444f3-3 --source recent-unwrapped --lines 120
# with ANSI colours preserved
herdr pane read w651d456f8444f3-3 --source visible --ansi
herdr workspace list
herdr workspace create --cwd /path/to/project
herdr workspace create --cwd /path/to/project --label "api server"
herdr workspace create --no-focus
herdr workspace focus w651d456f8444f3
herdr workspace rename w651d456f8444f3 "api server"
herdr workspace close w651d456f8444f3
herdr tab list --workspace w651d456f8444f3
herdr tab create --workspace w651d456f8444f3
herdr tab create --workspace w651d456f8444f3 --label "logs"
herdr tab rename w651d456f8444f3:2 "logs"
herdr tab focus w651d456f8444f3:2
herdr tab close w651d456f8444f3:2
herdr pane close w651d456f8444f3-3
install built-in agent integrations for more precise state detection:
herdr integration install pi
herdr integration install claude
herdr integration install codex
herdr integration install opencode
herdr integration status
uninstall:
herdr integration uninstall pi
herdr session list
herdr session attach work
herdr session stop work
select a session for CLI commands:
HERDR_SESSION=side-project herdr workspace list
# split a new pane
RESPONSE=$(herdr pane split w651d456f8444f3-2 --direction right --no-focus)
NEW_PANE=$(echo "$RESPONSE" | python3 -c 'import sys,json; print(json.load(sys.stdin)["result"]["pane"]["pane_id"])')
# start the server
herdr pane run "$NEW_PANE" "npm run dev"
# wait for it to be ready
herdr wait output "$NEW_PANE" --match "ready" --timeout 30000
# read the output
herdr pane read "$NEW_PANE" --source recent --lines 20
herdr pane split w651d456f8444f3-2 --direction down --no-focus
herdr pane run w651d456f8444f3-3 "cargo test"
herdr wait output w651d456f8444f3-3 --match "test result" --timeout 60000
herdr pane read w651d456f8444f3-3 --source recent --lines 30
herdr pane list
herdr pane read w651d456f8444f3-3 --source recent --lines 80
# inspect what is already there
herdr pane read w651d456f8444f3-3 --source recent --lines 40
# wait for specific output
herdr wait output w651d456f8444f3-3 --match "ready" --timeout 30000
# read unwrapped transcript that the waiter matched
herdr pane read w651d456f8444f3-3 --source recent-unwrapped --lines 40
# split pane and start the agent
herdr pane split w651d456f8444f3-2 --direction right --no-focus
herdr pane run w651d456f8444f3-3 "pi"
# wait for the agent prompt
herdr wait output w651d456f8444f3-3 --match "thinking" --timeout 30000
# give it a task
herdr pane run w651d456f8444f3-3 "review the test coverage in src/api/"
# wait for it to finish
herdr wait agent-status w651d456f8444f3-3 --status idle --timeout 120000
# read the result
herdr pane read w651d456f8444f3-3 --source recent --lines 100
# close when done
herdr pane close w651d456f8444f3-3
# wait for the agent to finish
herdr wait agent-status w651d456f8444f3-3 --status done --timeout 120000
# read its output
herdr pane read w651d456f8444f3-3 --source recent --lines 100
# send first message
herdr pane run w651d456f8444f3-3 "review the test coverage"
# wait until idle
herdr wait agent-status w651d456f8444f3-3 --status idle --timeout 120000
# read response
herdr pane read w651d456f8444f3-3 --source recent --lines 80
# send follow-up
herdr pane run w651d456f8444f3-3 "also check src/utils/"
# wait again
herdr wait agent-status w651d456f8444f3-3 --status idle --timeout 120000
# read again
herdr pane read w651d456f8444f3-3 --source recent --lines 80
herdr pane list prints json. parse result.panes[].pane_id for pane ids and result.panes[].focused to find your pane.herdr pane split prints json. the new pane id is at result.pane.pane_id.herdr workspace create prints json with result.workspace, result.tab, and result.root_pane.herdr tab create prints json with result.tab and result.root_pane.herdr pane read prints text, not json.herdr pane send-text, herdr pane send-keys, and herdr pane run print nothing on success.herdr pane read --ansi or herdr pane read --format ansi returns a rendered ANSI snapshot.herdr pane read --source recent-unwrapped joins soft wraps — use it to inspect the same transcript that wait output matches against.herdr pane run <id> "cmd" sends text + \r (enter). the command runs in the pane's existing shell process — it does not start a new shell.herdr pane send-text <id> "text" sends text without enter. use herdr pane send-keys <id> Enter to press enter.herdr pane send-keys accepts special keys: Enter, Up, Down, Left, Right, Backspace, Tab, etc.--no-focus on pane split, tab create, and workspace create keeps your current terminal context focused.herdr pane read for current output that already exists. use herdr wait output for future output you expect next.HERDR_ENV environment variable is set to 1.HERDR_SESSION=<name> selects a named session for CLI commands. HERDR_SOCKET_PATH is a low-level override.--wait flag on pane run or pane send-text. to pace messages to an agent, use herdr wait agent-status --status idle between sends.w651d456f8444f3-2. always re-read ids from herdr pane list — do not hardcode or guess.> file or | tee. use herdr pane read and herdr wait output instead.herdr wait output exit code is 1 on timeout.herdr agent subcommands do not exist in v0.5.8. use herdr pane commands for all pane interaction.development
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
tools
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
data-ai
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
tools
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.