agent-deck
/agent-deck
Zarządza sesjami agent-deck, terminalowego menedżera sesji agentów AI: tworzenie, start, wiadomości, fork, restart, podłączanie MCP, grupy, profile i sesje git worktree.
- Autor
- asheshgoplani ↗
- Repozytorium
- agent-deck ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 25.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 67
- Skrypty
- 29
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 2
Brak sygnałów. Repozytorium zmienione 25.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 29 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: evals/check.py, evals/run.sh, scripts/contributing/self-check.sh, scripts/goal/goal.sh, scripts/goal/manager.py, scripts/goal/tests/test_manager.py, scripts/goal/tests/test_progress_gate.py, scripts/goal/tests/test_run_budget.py, scripts/goal/tests/test_worker_prompt.py, scripts/launch-subagent.sh, scripts/repro/run.py, scripts/repro/test_validate.py, scripts/repro/validate.py, scripts/retro/measu
Co robi i kiedy
Zarządza sesjami agent-deck, terminalowego menedżera sesji agentów AI: tworzenie, start, wiadomości, fork, restart, podłączanie MCP, grupy, profile i sesje git worktree.
Wyzwalacze z opisu
Oryginalny opis (EN)
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; fan out a fleet of child sessions and check them non-blockingly; export or import a session for a teammate ("share session"); tag sessions and find past conversations (recall); run a local retrospecti
Jak działa
- Scripts
- Essential Commands
- Rules
- Configuration
- Where to Look Next
Podgląd SKILL.md
---
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; fan out a fleet of child sessions and check them non-blockingly; export or import a session for a teammate ("share session"); tag sessions and find past conversations (recall); run a local retrospective over their own transcripts, or reproduce an agent-deck bug and prove its fix; set up conductors or watchers; configure config.toml; troubleshoot agent-deck; or work on the agent-deck repo itself (fix, add or review its code or docs, open or fix a PR). Not for in-conversation subagents, plain git worktrees, plain tmux, team or sprint retrospectives, or bugs in projects other than agent-deck.
metadata:
compatibility: "claude, codex, opencode"
---
# Agent Deck
> Run `agent-deck --version` for your installed version. This skill targets v1.16.11+; most patterns work back to v1.7. See [Backward Compatibility](references/gotchas.md#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:
```bash
SKILL_DIR="/path/shown/in/base-directory-line"
$SKILL_DIR/scripts/launch-subagent.sh "Title" "Prompt" --wait
```
Plugin 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 command --json <name> "/compact"` | Run a Claude Code slash command or skill (`/model`, `/compact`, `/clear`, `/exit`) safely and verify it; never via `session send`. `session commands --json <name>` lists them |
| `agent-deck session ref <source> <target>` | Type a short reference to `<source>` (title, id, path, status, how to read it) into `<target>`'s composer, not sent; `--print` only prints it |
| `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 open report.html` | Show an HTML report to the user in the macOS app Browser panel (works from remote sessions too) |
| `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](references/cli-reference.md).
## Rules
1. **Flags before arguments:** `session start -m "Hello" name` always works. Since 0.12.0 nearly every subcommand (`session`, `add`, `launch`, `group`, `worktree`, `try`, ...) also accepts flags after the positional, so on a current build a flag after the name is not why it was ignored (older builds dropped it); only `config show [path]` and `openclaw send <message>` stop parsing at the first positional, so there a flag after it is ignored or read as text. Everything after `--` is positional.
2. **MCPs on request only:** attach one when the user asks, then `session restart` it; attaching alone does not load it. `--global` writes Claude's config for every project; the default writes the session's `.mcp.json`.
3. **Leave other sessions to work:** read another session with a single `session output` or `session children` call rather than a polling loop, which can interfere with the target.
4. **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_FILE` for custom `--cmd`), so a prompt need not explain who the child is or how to reach its parent. Opt out with `--no-identity` or `[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, but only when the XDG file does not exist; once it does, the legacy file is ignored). Every option is in [config-reference.md](references/config-reference.md).
## 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](references/capabilities.md) |
| Sessions messaging each other, `send` delivery guarantees, `output`, `children`, `inbox drain`, `handoff`, send pitfalls | [session-communication.md](references/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](references/sub-agents.md) |
| Fanning out several children and supervising them non-blockingly | [fleet.md](references/fleet.md) |
| Conductors (`conductor setup`), Telegram/Slack channels, watchers (webhook, GitHub, ntfy, Slack) | [conductors.md](references/conductors.md), then [documentation/WATCHERS.md](https://github.com/asheshgoplani/agent-deck/blob/main/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](references/session-workflows.md) |
| Self-improvement (transcript mining), goals (goal-driven worker autonomy), trust-but-verify for completion claims | [autonomy.md](references/autonomy.md), then [self-improvement.md](references/self-improvement.md) or [goal.md](references/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](references/gotchas.md) |
| TUI keys, dialogs, search, and layout | [tui-reference.md](references/tui-reference.md) |
| A session in error, MCPs not loading, diagnostics, getting help, or filing a bug | [troubleshooting.md](references/troubleshooting.md) |
| Docker sandboxed sessions | [sandbox.md](references/sandbox.md) |
| Durable session hints and tags, the cross-harness transcript index, `recall context --into current`, federated search, the recall MCP server | [recall.md](references/recall.md) |
| Exporting or importing a session for another developer | [session-share.md](references/session-share.md) |
| A local retrospective over the user's own transcripts, Recall index and logs (repeated failures, retries, stuck sessions); privacy rules and the pause-for-the-user-to-file handoff | [retro.md](references/retro.md), metrics in [retro-metrics.md](references/retro-metrics.md) |
| Reproducing an agent-deck bug in isolation and proving a fix (reproduced / not reproduced / fixed verdicts, receipts, the result contract) | [repro.md](references/repro.md), then [repro-contract.md](references/repro-contract.md) |
| User-level vs pool skills, attaching and detaching skills | [documentation/SKILLS.md](https://github.com/asheshgoplani/agent-deck/blob/main/documentation/SKILLS.md) |
| Working on the agent-deck repo itself: fix, add or review something in its code or docs, open a PR, answer an intake or review verdict | [contributing.md](references/contributing.md); it mirrors the PR intake gate and runs `scripts/contributing/self-check.sh` (tests only in a container) |
Pliki w paczce (67)
- SKILL.md 9 KB
- evals/RUNNER.md 5 KB
- evals/check.py 30 KB
- evals/drift-allow.json 1 KB
- evals/evals.json 225 KB
- evals/promises.json 115 KB
- evals/run.sh 3 KB
- references/autonomy.md 12 KB
- references/capabilities.md 7 KB
- references/cli-reference.md 125 KB
- references/conductors.md 6 KB
- references/config-reference.md 157 KB
- references/contributing-gate-spec.md 9 KB
- references/contributing-pr-body-template.md 4 KB
- references/contributing-security-self-scan.md 5 KB
- references/contributing.md 9 KB
- references/fleet.md 17 KB
- references/goal.md 34 KB
- references/gotchas.md 19 KB
- references/recall.md 14 KB
- references/repro-contract.md 4 KB
- references/repro.md 5 KB
- references/retro-metrics.md 2 KB
- references/retro.md 7 KB
- references/sandbox.md 13 KB
- references/self-improvement.md 9 KB
- references/session-communication.md 10 KB
- references/session-share.md 7 KB
- references/session-workflows.md 14 KB
- references/sub-agents.md 11 KB
- references/troubleshooting.md 19 KB
- references/tui-reference.md 22 KB
- scripts/launch-subagent.sh 6 KB
- scripts/contributing/self-check.sh 19 KB
- scripts/goal/goal.sh 10 KB
- scripts/goal/manager.py 41 KB
- scripts/goal/prompts/worker.md 6 KB
- scripts/goal/tests/test_manager.py 20 KB
- scripts/goal/tests/test_progress_gate.py 31 KB
- scripts/goal/tests/test_run_budget.py 15 KB
- scripts/goal/tests/test_worker_prompt.py 5 KB
- scripts/repro/run.py 4 KB
- scripts/repro/test_validate.py 4 KB
- scripts/repro/validate.py 5 KB
- scripts/retro/config.example.json 1 KB
- scripts/retro/measure.py 14 KB
- scripts/retro/test_measure.py 5 KB
- scripts/retro/wakes.py 14 KB
- scripts/self-improvement/analyze-all-conductors.sh 5 KB
- scripts/self-improvement/build_manifest.py 6 KB
- scripts/self-improvement/distill.py 9 KB
- scripts/self-improvement/file-issues.sh 9 KB
- scripts/self-improvement/file_issue.py 5 KB
- scripts/self-improvement/list_candidates.py 8 KB
- scripts/self-improvement/rules.json 1 KB
- scripts/self-improvement/run-analyzers.sh 3 KB
- scripts/self-improvement/sanitize.py 11 KB
- scripts/self-improvement/prompts/analyzer.md 4 KB
- scripts/self-improvement/prompts/auditor.md 4 KB
- scripts/self-improvement/prompts/issue-drafter.md 3 KB
- scripts/self-improvement/prompts/sanitizer.md 5 KB
- scripts/self-improvement/prompts/synthesizer.md 4 KB
- scripts/session-share/export.sh 7 KB
- scripts/session-share/import.sh 7 KB
- scripts/session-share/utils.sh 4 KB
- tests/test_launch_subagent.sh 7 KB
- tests/test_session_share_export_895_regression.sh 4 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · asheshgoplani/agent-deck | 100 | MIT |
| HelixDevelopment/agent | 100 | MIT |
Identyczna treść występuje jeszcze w 1 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.
Migawka bazy z 13.11.2026 · wersja paczki 53e39e2d5d61 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100sessions
Listuje i czyta sesje oraz wątki agentów, a także dopasowuje worktree lub proces do sesji. - 100codex-deck-flow
Prowadzi trwałe wieloagentowe przepływy kodowania z zależnościami zadań, sesjami Codex per zadanie, izolacją przez git worktree i jawnym scalaniem, opartymi na jednym pliku JSON w ./.codex-deck/. - 100session-mention
Naprawia wysyłanie wiadomości między sesjami Claude Code przez @nazwę sesji i podpowiada, jak nazywać sesje, by dało się je zaadresować. - 100fork-worktree
Tworzy nową gałąź autonomii z osobnym worktree, co ułatwia równoległe przepływy pracy agentów. - 100session-lifecycle
Zarządza sesjami agentów w Claude Agent SDK i Managed Agents: wznawianie, forkowanie, identyfikatory i retencja. - 100parallel-work
Prowadzi kilka zadań naraz, każde we własnym drzewie roboczym i sesji, koordynowanych z głównego katalogu.