Puppetmaster Agent Orchestration
professorpalmer/Puppetmaster
Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.
agent-deck, the terminal session manager for AI coding agents.
Install Agent Deck
$ npx skills add asheshgoplani/agent-deck --skill agent-deck -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install asheshgoplani/agent-deck agent-deck --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/asheshgoplani/agent-deck.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-deck .claude/skills/agent-deck && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-deck" agent skill from https://github.com/asheshgoplani/agent-deck/tree/main/skills/agent-deck into .claude/skills/agent-deck/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-deck", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/asheshgoplani/agent-deck/tree/main/skills/agent-deckType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add asheshgoplani/agent-deck --skill agent-deck -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install asheshgoplani/agent-deck agent-deck --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asheshgoplani/agent-deck.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-deck .agents/skills/agent-deck && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-deck" agent skill from https://github.com/asheshgoplani/agent-deck/tree/main/skills/agent-deck into .agents/skills/agent-deck/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-deck", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asheshgoplani/agent-deck --skill agent-deck -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install asheshgoplani/agent-deck agent-deck --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asheshgoplani/agent-deck.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-deck .cursor/skills/agent-deck && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-deck" agent skill from https://github.com/asheshgoplani/agent-deck/tree/main/skills/agent-deck into .cursor/skills/agent-deck/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-deck", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/asheshgoplani/agent-deck.git --path skills/agent-deck--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add asheshgoplani/agent-deck --skill agent-deck -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install asheshgoplani/agent-deck agent-deck --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asheshgoplani/agent-deck.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-deck .gemini/skills/agent-deck && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-deck" agent skill from https://github.com/asheshgoplani/agent-deck/tree/main/skills/agent-deck into .gemini/skills/agent-deck/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-deck", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install asheshgoplani/agent-deck agent-deckInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add asheshgoplani/agent-deck --skill agent-deck -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/asheshgoplani/agent-deck.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-deck .github/skills/agent-deck && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-deck" agent skill from https://github.com/asheshgoplani/agent-deck/tree/main/skills/agent-deck into .github/skills/agent-deck/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-deck", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asheshgoplani/agent-deck --skill agent-deck -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install asheshgoplani/agent-deck agent-deck --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asheshgoplani/agent-deck.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-deck .opencode/skills/agent-deck && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-deck" agent skill from https://github.com/asheshgoplani/agent-deck/tree/main/skills/agent-deck into .opencode/skills/agent-deck/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-deck", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-deck- GitHub stars
- 1k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 653 words
- Files
- 42 (incl. scripts, references)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
agent-deck, the terminal session manager for AI coding agents.
- Works in 4 steps: Flags before arguments: session start -m… → MCPs on request only: attach one when… → Leave other sessions to work: read… → …
- The user mentions agent-deck
- SKILL.md covers Scripts, Essential Commands, Rules and Configuration, plus 1 more section
- Needs to create
What it does
Agent Deck is an agent skill from asheshgoplani/agent-deck. agent-deck, the terminal session manager for AI coding agents. Use when the user mentions "agent-deck", "session", "sub-agent", "MCP attach", or "git worktree", or needs to create, start, message, read, fork, restart, or supervise agent-deck sessions; launch child sessions or consult another CLI through agent-deck; attach MCPs to a session; manage groups, profiles, accounts, or worktree sessions; set up conductors or watchers; configure config.toml; or troubleshoot agent-deck. Not for in-conversation subagents…
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 44 other files, including scripts and reference files (for example `evals/RUNNER.md`, `evals/evals.json` and `references/autonomy.md`).
It sits in Agent Workflows, covering Git worktrees, MCP servers and Subagents. It works with Model Context Protocol, tmux and Git. The repository describes itself as: Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more. The licence is MIT.
When your agent uses it
- The user mentions agent-deck
- Needs to create
- Supervise agent-deck sessions
- Launch child sessions
Example prompts
- “agent-deck”
- “session”
- “sub-agent”
- “/agent-deck”
Requirements
- Docker
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Flags before arguments: session start -m "Hello" name, not name -m "Hello". A flag that seems ignored is almost always in the wrong…
- MCPs on request only: attach one when the user asks, then session restart it; attaching alone does not load it. --global writes Claude's…
- Leave other sessions to work: read another session with a single session output or session children call rather than a polling loop, which…
- State only the task in a child's prompt. Every session agent-deck launches already carries its identity (session id, title, parent, core…
What it can do on your machine
Read from SKILL.md and the folder at commit 34cf369. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Deck loads about 1.7k tokens when it runs, and up to ~96k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 653 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from asheshgoplani/agent-deck at commit 34cf369, republished under its MIT licence (© asheshgoplani). 653 words, ~1,721 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-deck/SKILL.md (or your agent's skills folder). This skill also uses 41 other files; get the full folder from GitHub.- name
- agent-deck
- description
- agent-deck, the terminal session manager for AI coding agents. Use when the user mentions "agent-deck", "session", "sub-agent", "MCP attach", or "git worktree", or needs to create, start, message, read, fork, restart, or supervise agent-deck sessions; launch child sessions or consult another CLI through agent-deck; attach MCPs to a session; manage groups, profiles, accounts, or worktree sessions; set up conductors or watchers; configure config.toml; or troubleshoot agent-deck. Not for in-conversation subagents, plain git worktrees, or plain tmux.
- metadata.compatibility
- claude, codex, opencode
Agent Deck
Run
agent-deck --versionfor your installed version. This skill targets v1.16.11+; most patterns work back to v1.7. See Backward Compatibility for what needs ≥1.16.11.
Scripts
Helper scripts live in this skill's scripts/ folder. Resolve them from the base directory shown when the skill loaded, not from the user's project:
SKILL_DIR="/path/shown/in/base-directory-line"
$SKILL_DIR/scripts/launch-subagent.sh "Title" "Prompt" --waitPlugin installs resolve to ~/.claude/plugins/cache/agent-deck/agent-deck/<hash>/skills/agent-deck/; a repo checkout resolves to <repo>/skills/agent-deck/.
Essential Commands
| Command | Purpose |
|---|---|
agent-deck | Launch interactive TUI |
agent-deck add -t "Name" -c claude /path | Create session |
agent-deck launch . -c claude --account <name> | Create and start a session under a named account slot |
agent-deck session start/stop/restart <name> | Control session |
agent-deck session send <name> "message" | Send message |
agent-deck session send <name> --message-file <file> | Send message from file (- = stdin); no shell quoting. Also on launch/session start |
agent-deck session output <name> | Get bounded, ANSI-clean last response (JSON/quiet/copy preserve full source) |
agent-deck session children --json | Child sessions' live status + asserted completions (non-blocking, read-only) |
agent-deck session current [-q|--json] | Auto-detect current session |
agent-deck session fork <name> | Fork Claude/OpenCode/Pi/Codex/Oh My Pi conversation |
agent-deck mcp list | List available MCPs |
agent-deck mcp attach <name> <mcp> | Attach MCP (then restart) |
agent-deck status | Quick status summary |
agent-deck add --worktree <branch> | Create session in git worktree |
Status: ● running | ◐ waiting | ○ idle | ✕ error
Every other command and flag is in cli-reference.md.
Rules
- Flags before arguments:
session start -m "Hello" name, notname -m "Hello". A flag that seems ignored is almost always in the wrong position. - MCPs on request only: attach one when the user asks, then
session restartit; attaching alone does not load it.--globalwrites Claude's config for every project; the default writes the session's.mcp.json. - Leave other sessions to work: read another session with a single
session outputorsession childrencall rather than a polling loop, which can interfere with the target. - State only the task in a child's prompt. Every session agent-deck launches already carries its identity (session id, title, parent, core commands, completion sentinel;
$AGENTDECK_IDENTITY_FILEfor custom--cmd), so a prompt need not explain who the child is or how to reach its parent. Opt out with--no-identityor[launch] inject_identity = false; gemini also needs its identity folder trusted (documentation/HARNESS_IDENTITY.md).
Configuration
$XDG_CONFIG_HOME/agent-deck/config.toml (default ~/.config/agent-deck/config.toml; legacy ~/.agent-deck/config.toml still honored). Every option is in config-reference.md.
Show full SKILL.md (281 more words)Show less
Where to Look Next
Read the matching reference before acting on anything beyond the commands above.
| When the task involves | Read |
|---|---|
What agent-deck and each session's CLI (claude, codex, gemini) can do; choosing the -c tool for a child | capabilities.md |
Sessions messaging each other, send delivery guarantees, output, children, inbox drain, handoff, send pitfalls | session-communication.md |
Launching a sub-agent (launch-subagent.sh), retrieval modes, worker prompt conventions, the ===AGENTDECK_DONE=== completion sentinel, consulting Codex or Gemini, root-level peers (-no-parent) | sub-agents.md |
| Fanning out several children and supervising them non-blockingly | fleet skill |
Conductors (conductor setup), Telegram/Slack channels, watchers (webhook, GitHub, ntfy, Slack) | conductors.md, then documentation/WATCHERS.md for custom watchers |
Context inspection (session context), worktrees, scratch sessions (try), runtime health (health, dead letters, remote update --from-build), recall hints and search, session sharing, switching a session to another Claude account | session-workflows.md |
| Self-improvement (transcript mining), goals (goal-driven worker autonomy), trust-but-verify for completion claims | autonomy.md, then self-improvement.md or goal.md for the deep dive |
Using agent-deck as a daemon supervisor (it is not one), known gotchas and workarounds (--no-wait Enter fallback, text file busy, -c "claude <subcommand>", config drift, channel subscription, Telegram conductor topology, v1.9.x findings), and what needs a deck newer than 1.16.11 | gotchas.md |
| TUI keys, dialogs, search, and layout | tui-reference.md |
| A session in error, MCPs not loading, diagnostics, getting help, or filing a bug | troubleshooting.md |
| Docker sandboxed sessions | sandbox.md |
Durable session hints and tags, the cross-harness transcript index, recall context --into current, federated search, the recall MCP server | recall skill |
| Exporting or importing a session for another developer | session-share skill |
| User-level vs pool skills, attaching and detaching skills | documentation/SKILLS.md |
| Fixing agent-deck itself and opening a PR | .github/skills/agent-deck-contributor/SKILL.md in an agent-deck checkout; it mirrors the PR intake gate and runs tests sandboxed |
© asheshgoplani, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 41 other files (scripts, references) in skills/agent-deck of asheshgoplani/agent-deck.
- SKILL.md
- evals/RUNNER.md
- evals/evals.json
- references/autonomy.md
- references/capabilities.md
- references/cli-reference.md
- references/conductors.md
- references/config-reference.md
- references/goal.md
- references/gotchas.md
- references/sandbox.md
- references/self-improvement.md
- references/session-communication.md
- references/session-workflows.md
- references/sub-agents.md
- references/troubleshooting.md
- references/tui-reference.md
- scripts/goal
- … and 24 more
Open the folder on GitHubat commit 34cf369
Compare with similar skills
Agent Deck next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Deck this skillasheshgoplani/agent-deck | 1k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster | 467 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Vibe Kanbanaiskillstore/marketplace | 430 | — | ~4.4k | Automated safety check: Notes | None | |
| Clawteamwin4r/ClawTeam-OpenClaw | 1.5k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Agtx Task Sweepfynnfluegge/agtx | 1.7k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Run Wavejpicklyk/task-orchestrator | 207 | — | ~4.7k | Automated safety check: Pass | MIT |
Similar skills
Vibe Kanban
aiskillstore/marketplace
Manage AI coding agents on a visual Kanban board. An agent skill from aiskillstore/marketplace.
Clawteam
win4r/ClawTeam-OpenClaw
Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.
Agtx Task Sweep
fynnfluegge/agtx
Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.
Run Wave
jpicklyk/task-orchestrator
Resolves ready MCP work items into a run plan, shows it to you, then executes it through the Workflow tool or direct subagent dispatch, with post-run verification.
Devcontainer Dev
stacklok/toolhive-studio
Spin up and interact with ToolHive Studio's containerized dev environment (Xvfb + noVNC + DinD).
More from asheshgoplani/agent-deck
Deck Retro
asheshgoplani/agent-deck
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs.
Session Share
asheshgoplani/agent-deck
Share Claude Code sessions between developers. An agent skill from asheshgoplani/agent-deck.
Deck Repro
asheshgoplani/agent-deck
Reproduce agent-deck bugs from an issue, transcript excerpt, or description in an isolated environment, and prove fixes with the same reproduction and a regression test.
Agent Deck Recall
asheshgoplani/agent-deck
Record and later find what an agent-deck session was for, across harnesses, and hand a past conversation to the current one.
Fleet
asheshgoplani/agent-deck
Fan out a fleet of independent agent-deck child sessions from inside a session and check their progress non-blockingly.
Watcher Creator
asheshgoplani/agent-deck
Guide for creating agent-deck watchers conversationally. An agent skill from asheshgoplani/agent-deck.
Related
Works with
Categories
Questions about Agent Deck
What does Agent Deck do?
agent-deck, the terminal session manager for AI coding agents. Agent Deck is an agent skill from asheshgoplani/agent-deck. agent-deck, the terminal session manager for AI coding agents.
When should I use Agent Deck?
Agent Deck fits situations like: the user mentions agent-deck; needs to create; supervise agent-deck sessions; launch child sessions.
How do I install Agent Deck in Claude Code?
Run `npx skills add asheshgoplani/agent-deck --skill agent-deck -a claude-code`. Or copy the skill folder (skills/agent-deck in asheshgoplani/agent-deck) into .claude/skills/agent-deck in your project. Claude Code loads it when a task matches its description.
How do I install Agent Deck in Codex?
Run `npx skills add asheshgoplani/agent-deck --skill agent-deck -a codex`. Or copy the skill folder (skills/agent-deck in asheshgoplani/agent-deck) into .agents/skills/agent-deck in your project. Codex loads it when a task matches its description.
Can I use Agent Deck in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add asheshgoplani/agent-deck --skill agent-deck -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-deck, .gemini/skills/agent-deck, .github/skills/agent-deck and .opencode/skills/agent-deck in your project.
What does Agent Deck need to run?
SKILL.md names no scripts, command-line tools or credentials: Agent Deck is instructions for the agent only. Our summary lists: Docker.
Does Agent Deck access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Agent Deck safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Agent Deck use?
Agent Deck is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Deck use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 94k tokens, read only when the agent opens those files.
What are the alternatives to Agent Deck?
Skills that share tags, products or a category with Agent Deck: Puppetmaster Agent Orchestration (professorpalmer/Puppetmaster, 467 stars), Vibe Kanban (aiskillstore/marketplace, 430 stars), Clawteam (win4r/ClawTeam-OpenClaw, 1.5k stars) and Agtx Task Sweep (fynnfluegge/agtx, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Deck?
asheshgoplani (a GitHub user) maintains it in asheshgoplani/agent-deck, which has 1,034 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 5, 2026.
Source: asheshgoplani/agent-deck on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.