Agent presets
How enowX starts each agent (core/agent). Sessions start with permission prompts skipped when Skip permission prompts is on in the New session dialog (the default), and keep that setting when the daemon restarts them with continue.
| Agent | Command | First prompt | Skip permission prompts | Continue last conversation | Source |
|---|---|---|---|---|---|
| Claude Code | claude | last argument | --dangerously-skip-permissions | --continue (per directory) | CLI reference, permission modes |
| Codex | codex | last argument | --dangerously-bypass-approvals-and-sandbox (alias --yolo) | resume --last (filtered to the working directory) | codex-rs/utils/cli/src/shared_options.rs, codex-rs/cli/src/main.rs in openai/codex |
| OpenCode | opencode | --prompt | --auto (explicit deny rules still apply) | --continue | packages/web/src/content/docs/{cli,permissions}.mdx in sst/opencode |
| Gemini CLI | gemini | --prompt-interactive | --yolo | --resume latest (per project root) | docs/reference/configuration.md, docs/cli/session-management.md in the npm package |
| Kiro CLI | kiro-cli chat | last argument | --trust-all-tools | --resume (per directory) | Unverified: Kiro’s docs were unreachable; flags are those of its predecessor’s open-source chat command |
More agents, started the same way; their flags are those their documentation gives, not all checked by running them. Agents that take no first prompt on their command line get it typed in, as a paste, once their screen settles. An agent found under its alias runs as that. A program that only shares an agent’s name doesn’t count as installed: the database tool goose (goose --version says goose version: v…) isn’t the Goose agent.
| Agent | Command | First prompt | Skip permission prompts | Continue last conversation | Source |
|---|---|---|---|---|---|
| Claude Agent Teams | claude | last argument | --dangerously-skip-permissions · always CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 | --continue | docs |
| OpenClaude | openclaude | last argument | --dangerously-skip-permissions | --continue | docs |
| Grok | grok | -- | --permission-mode bypassPermissions | — | docs |
| GitHub Copilot | copilot | -i | --yolo | — | docs |
| OpenCode 2 | opencode2 --standalone | --prompt | — | — | docs |
| MiMo Code | mimo | --prompt | — | — | docs |
| Ante | ante | typed in once it shows its input | --yolo | — | docs |
| Trae | traecli | -- | --yolo | — | docs |
| Muse | muse --trust-workspace | typed in once it shows its input | --yolo | — | docs |
| DeepSeek Harness | dsh-tui . (also dst) | typed in once it shows its input | — | — | docs |
| Qoder CLI | qodercli (also qoder) | --prompt-interactive | --dangerously-skip-permissions | — | docs |
| Qoder CLI China | qoderclicn (also qodercn) | --prompt-interactive | --dangerously-skip-permissions | — | docs |
| ZCode | zcode | typed in once it shows its input | --mode yolo | — | docs |
| Pi | pi | last argument | — | — | docs |
| OMP | omp | last argument | --auto-approve | --continue | docs |
| Prime Agent | prime-agent | -- | — | — | docs |
| Antigravity | agy | --prompt-interactive | --dangerously-skip-permissions | — | docs |
| Aider | aider | typed in once it shows its input | --yes-always | — | docs |
| Goose | goose --version | typed in once it shows its input | GOOSE_MODE=auto in its environment · always GOOSE_MODE=auto | — | docs |
| Amp | amp | typed in once it shows its input | --dangerously-allow-all | — | docs |
| Kilo Code | kilo | typed in once it shows its input | — | — | docs |
| Crush | crush | typed in once it shows its input | --yolo | — | docs |
| Auggie | auggie | typed in once it shows its input | — | — | docs |
| Autohand Code | autohand | typed in once it shows its input | --unrestricted | — | docs |
| Cline | cline | typed in once it shows its input | --auto-approve true | — | docs |
| Codebuff | codebuff | typed in once it shows its input | — | — | docs |
| Freebuff | freebuff | typed in once it shows its input | — | — | docs |
| Command Code | command-code --trust | last argument | --yolo | — | docs |
| Continue | cn | typed in once it shows its input | --allow * | — | docs |
| Cursor | cursor-agent | last argument | --yolo | — | docs |
| Droid | droid | last argument | --auto high | — | docs |
| Kimi | kimi (also kimi-code) | typed in once it shows its input | --yolo | — | docs |
| Mistral Vibe | vibe (also mistral-vibe) | typed in once it shows its input | --agent auto-approve | — | docs |
| Qwen Code | qwen | typed in once it shows its input | --approval-mode yolo | — | docs |
| Rovo Dev | acli rovodev run | typed in once it shows its input | --yolo | — | docs |
| Hermes | hermes --tui | --query | --yolo | — | docs |
| Devin | devin | typed in once it shows its input | --permission-mode bypass --respect-workspace-trust false | — | docs |
| OpenClaw | openclaw | typed in once it shows its input | — | — | docs |
| CodeBuddy | codebuddy (also cbc) | last argument | --dangerously-skip-permissions | — | docs |
| Jcode | jcode | typed in once it shows its input | — | — | docs |
Trusting the folder
Many agents ask, the first time they start in a folder, whether to trust it, and take no prompt until answered. The folder is the one picked for the session in enowX, which is that decision made, so for its first 30 seconds the daemon watches a new agent’s screen and answers once: a question with “trust” in it whose selected option (marked >, ❯, › or ▶) says yes or trust gets Enter (agent.TrustAsked). A first prompt typed in waits for that. Checked on CodeBuddy Code and Antigravity CLI.
Installing
When an agent is missing, the New session dialog offers to install it: enowX shows the command, then runs it in a session on that host, as the user enowX runs as, so its output and questions stay visible. The daemon reads the login shell’s PATH again when the agent list is asked for, so the new agent shows up without a restart.
| Agent | Install command | Source |
|---|---|---|
| Claude Code | curl -fsSL https://claude.ai/install.sh | bash | README of anthropics/claude-code |
| Codex | curl -fsSL https://chatgpt.com/codex/install.sh | sh | README of openai/codex |
| OpenCode | curl -fsSL https://opencode.ai/install | bash | docs/index.mdx in sst/opencode |
| Gemini CLI | npm install -g --prefix "$HOME/.local" @google/gemini-cli | README of google-gemini/gemini-cli (npm install -g); the prefix avoids needing root |
| Kiro CLI | curl -fsSL https://cli.kiro.dev/install | bash | Kiro’s CLI install page, as given by the user (unreachable from enowX’s build machine) |
| Aider, Amp, Goose, Cursor, Droid | their official install scripts (core/agent/presets.go) | each agent’s install docs |
| GitHub Copilot, Qwen Code, Crush, Auggie, Cline, Codebuff, Kilo Code, Continue | npm install -g --prefix "$HOME/.local" <package> | each agent’s npm package |
Agents with no install command enowX knows link to their documentation instead.
Signing in
Agents run inside a small /bin/sh wrapper (PowerShell on Windows) that starts the login shell once the agent exits, so quitting it with Ctrl+C, or a failed sign-in, leaves a prompt in the same folder. The New session dialog’s Sign in runs the command below in the project folder, which prints a link and a code to open on any device; this is what works on a server without a browser.
| Agent | Sign-in command | Source |
|---|---|---|
| Claude Code | claude auth login | Claude Code docs (claude auth status), error guides; prints a URL and asks for the code |
| Codex | codex login --device-auth | Codex auth docs; a ChatGPT workspace admin must allow device codes |
| OpenCode | opencode auth login | OpenCode CLI docs; most providers take an API key |
| Gemini CLI | NO_BROWSER=true gemini | Gemini CLI authentication docs; it has no login command, its first screen signs in |
| Kiro CLI | kiro-cli login --use-device-flow | Kiro CLI’s own error message; Builder ID and IAM Identity Center only, Google and GitHub sign-in are refused remotely |
Status
The session list shows each agent as working, needing input, done with its turn, or idle. Agents with hooks report it themselves: enowX adds its hooks when it starts them, and they run "$ENOWX_BIN" hook <state> (or hook --event E --state S, which also hands the user’s hooks the event: hooks.md), where the daemon sets ENOWX_BIN to a launcher in the data folder (bin/enowx, written at each start of the daemon) in every session, so nothing changes in the user’s own configuration, the hooks do nothing outside enowX, and moving or replacing the app under a running daemon breaks no session: the launcher runs the program where the daemon started from, or else the same app in Applications. The app warns when it runs from outside Applications, and when it is moved while it runs. The other agents, and these between reports, go by their screen: one that changed within the last 1.5 s is working.
| Agent | How | Reports | Source |
|---|---|---|---|
| Claude Code | --settings '{"hooks": …}', merged with the user’s settings | UserPromptSubmit, PostToolUse, PostToolUseFailure → working; Notification matching permission_prompt|elicitation_dialog → needs input; Stop → done | Claude Code hooks docs; checked on 2.1.314 |
| Codex | -c notify=[…]: a /bin/sh wrapper that reports done, then runs the user’s own notify from config.toml with Codex’s argument; -c hooks.<Event>=[…], trusted by enowX in config.toml | end of each turn → done; UserPromptSubmit, PostToolUse → working; PermissionRequest → needs input | Codex notify config (agent-turn-complete), Codex hooks docs; checked on 0.164.0 |
| Every other agent | — | screen only |
Typing into an agent that asked something, or pressing Enter after it finished, ends that state; a working agent whose screen stood still for 15 s (interrupted, say) goes back to its screen. Hooks are POSIX shell, so on Windows every agent goes by its screen.
When an agent comes to need input or finishes its turn in a session you aren’t looking at, the app shows a desktop notification; clicking it opens the session.
Unread
A session whose agent finishes its turn or asks something while the user doesn’t see it (another session shown, another page, or the window not focused) turns unread: its name bold, with a dot, until it is shown. A tab’s agent marks its session. Mark as unread in a session’s menu keeps one to come back to.
Hibernation
After 30 minutes by default. Settings → New sessions → Hibernate idle agents (never, 15 minutes, 30 minutes, 1 hour, 4 hours; DaemonSettings.HibernateAfter, per host) lets the daemon stop an agent that its hooks say is done and that has shown and been typed nothing for that long: its program ends, what it started too, and its session stays, marked hibernated, showing what it showed. Showing the session continues it (session.continue), the agent coming back on its conversation. Only agents enowX can continue (Claude Code, Codex, OpenCode, Gemini CLI, Kiro CLI, …) and not tabs; agents without hooks never count as done, so they never hibernate. Nor does an agent whose session still serves a port (a dev server it started) or runs a desktop app on a virtual display: they would stop with it.
By hand
A session’s menu (right click in the session list) has Hibernate (⌘⇧H) and, for one hibernated, Wake; with several sessions selected (⌘-click or ⇧-click) it hibernates them all, and the project’s menu has Hibernate all idle. Before stopping work, the app asks: an agent working (hibernate now, once it is done, or cancel), a port served, an app on a display, a program left running in the background, each listed with the memory it holds and what hibernating frees (session.hibernate, its dryRun plan). Agents’ own helpers (their MCP servers, say) stop with them without asking. A session hibernated by hand is marked so in the list, with since when (SessionInfo.HibernatedHow); showing it, or Wake (session.wake), brings it back. It works on any host the app reaches, through its daemon.
Don’t hibernate on its own in a session’s menu keeps the daemon from hibernating it (session.autoHibernate, SessionInfo.NoAutoHibernate); Settings → New sessions sets it for new sessions, the same on every host (settings/hibernate.json, synced with the user’s data).
From an agent: enowx-app hibernate ID... [--idle] [--when-done] [--force] [--dry-run], enowx-app wake ID, hibernate ID --auto off|on, --auto-default off|on (MCP session_hibernate, session_wake); an agent asking has the user confirm in the app, and can’t hibernate its own session. ls shows hibernated or hibernated(by hand).
What agents are told
Every agent enowX starts is told what the session gives it (agent.Guide, which enowx-app guide prints): dev servers show in the Browser tool by themselves and it can drive that Browser, a desktop app on a server needs eval "$("$ENOWX_BIN" display)" first (see preview.md), the HTTP traffic of what it runs can be caught, read and mocked (traffic.md), Android devices can run and log its app (android.md), other agents can be started and followed, and note keeps the user posted. The same commands are MCP tools of enowx-app mcp, whose instructions are the guide.
It goes the way each agent takes standing instructions, and adds to the user’s own, never replacing them: flags that replace an agent’s system prompt are never used.
| Agent | How |
|---|---|
| Claude Code, Claude Agent Teams, OpenClaude, Qoder CLI, OMP, Prime Agent, Droid, Qwen Code, CodeBuddy | --append-system-prompt |
| Codex | -c developer_instructions=…, after the user’s own developer_instructions from config.toml, which -c would replace |
| Autohand Code | --append-sys-prompt |
| Grok | --rules |
| Continue | --rule |
| Aider | --read ~/.enowx-app/agent-guide.md |
| Auggie | --rules ~/.enowx-app/agent-guide.md |
| Kiro CLI | ~/.kiro/steering/enowx.md |
| GitHub Copilot | ~/.copilot/instructions/enowx.instructions.md |
| Antigravity | ~/.gemini/config/rules/enowx.md |
| Cline | ~/.cline/rules/enowx.md |
| Devin | ~/.devin/rules/enowx.md |
| Gemini CLI | a block of ~/.gemini/GEMINI.md |
| OpenCode, Kilo Code | instructions of the config in OPENCODE_CONFIG_CONTENT, KILO_CONFIG_CONTENT, naming ~/.enowx-app/agent-guide.md; nothing of the user’s is written |
| Ante | the same with ~/.ante/AGENTS.md |
| MiMo Code, ZCode, Amp, Command Code, Mistral Vibe, Rovo Dev | a block of ~/.config/mimocode/AGENTS.md, ~/.zcode/AGENTS.md, ~/.config/amp/AGENTS.md, ~/.commandcode/AGENTS.md, ~/.vibe/AGENTS.md, ~/.rovodev/AGENTS.md |
| Pi, Goose, Crush, Jcode | a block of ~/.pi/agent/APPEND_SYSTEM.md, ~/.config/goose/.goosehints, ~/.config/crush/CRUSH.md, ~/.jcode/prompt-overlay.md |
| Cursor, Kimi, OpenCode 2, Trae, Muse, DeepSeek Harness, Codebuff, Freebuff, Hermes, OpenClaw | none they read outside the project: a line after the first prompt says "$ENOWX_BIN" guide lists the tools |
Files are written, or brought up to date, when the daemon starts the agent. enowX’s own files (enowx.md) hold the whole guide. In a file of the user’s, enowX keeps only a short block between <!-- enowX: … --> lines, saying to run "$ENOWX_BIN" guide, and leaves the rest as it is; deleting the block is undone at the agent’s next start. Both apply only when ENOWX_SESSION is set, since the agent reads them outside enowX too. The places are those the agents’ documentation or source gives, not all checked by running them.
What each agent gets
The owner’s check of each in a real session is still to do: start one, ask who it is in enowX, have it name its enowX tools and call one. Until then every row says Not checked, whatever its source says. Sessions on the Notes and Canvas pages and GOD of Agents have tools of their own, and a teammate’s session gets no MCP server from here.
| Agent | Prompt | Tools | Knowledge | Source | Real session |
|---|---|---|---|---|---|
| Claude Code | --append-system-prompt | --mcp-config; the "$ENOWX_BIN" commands | The guide, whole, project rules included | CLI reference | Not checked |
| Codex | -c developer_instructions=, after the user’s own | -c mcp_servers.enowx.*; the "$ENOWX_BIN" commands | The guide, whole, project rules included | codex-rs config, rust-v0.166.0 | Not checked |
| OpenCode | instructions in OPENCODE_CONFIG_CONTENT, naming enowX’s file | mcp in OPENCODE_CONFIG_CONTENT; the "$ENOWX_BIN" commands | The guide, whole, project rules included | config.mdx, mcp-servers.mdx in sst/opencode | Not checked |
| Gemini CLI | a block of ~/.gemini/GEMINI.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | docs/reference/configuration.md in google-gemini/gemini-cli | Not checked |
| Kiro CLI | enowX’s ~/.kiro/steering/enowx.md | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Claude Agent Teams | --append-system-prompt | --mcp-config; the "$ENOWX_BIN" commands | The guide, whole, project rules included | CLI reference | Not checked |
| OpenClaude | --append-system-prompt | --mcp-config; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Grok | --rules | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| GitHub Copilot | enowX’s ~/.copilot/instructions/enowx.instructions.md | --additional-mcp-config; the "$ENOWX_BIN" commands | The guide, whole, project rules included | CLI reference | Not checked |
| OpenCode 2 | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | docs | Not checked |
| MiMo Code | a block of ~/.config/mimocode/AGENTS.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Ante | a block of ~/.ante/AGENTS.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Trae | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | docs; its rules page gave nothing to read | Not checked |
| Muse | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | configuration | Not checked |
| DeepSeek Harness | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | its page gave nothing to read (drawn by script) | Not checked |
| Qoder CLI | --append-system-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Qoder CLI China | --append-system-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| ZCode | a block of ~/.zcode/AGENTS.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Pi | a block of ~/.pi/agent/APPEND_SYSTEM.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| OMP | --append-system-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Prime Agent | --append-system-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Antigravity | enowX’s ~/.gemini/config/rules/enowx.md | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Aider | --read enowX’s file | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Goose | a block of ~/.config/goose/.goosehints, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Amp | a block of ~/.config/amp/AGENTS.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Kilo Code | instructions in KILO_CONFIG_CONTENT, naming enowX’s file | mcp in KILO_CONFIG_CONTENT; the "$ENOWX_BIN" commands | The guide, whole, project rules included | CLI, custom rules | Not checked |
| Crush | a block of ~/.config/crush/CRUSH.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Auggie | --rules enowX’s file | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Autohand Code | --append-sys-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Cline | enowX’s ~/.cline/rules/enowx.md | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Codebuff | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | its page gave nothing to read (drawn by script) | Not checked |
| Freebuff | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Command Code | a block of ~/.commandcode/AGENTS.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Continue | --rule | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Cursor | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | CLI, MCP | Not checked |
| Droid | --append-system-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Kimi | None found: a line after the first prompt | --mcp-config; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | command, MCP | Not checked |
| Mistral Vibe | a block of ~/.vibe/AGENTS.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Qwen Code | --append-system-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Rovo Dev | a block of ~/.rovodev/AGENTS.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
| Hermes | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | context files, MCP | Not checked |
| Devin | enowX’s ~/.devin/rules/enowx.md | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| OpenClaw | None found: a line after the first prompt | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | workspace | Not checked |
| CodeBuddy | --append-system-prompt | None for one session; the "$ENOWX_BIN" commands | The guide, whole, project rules included | the preset tables above; session flags not re-read | Not checked |
| Jcode | a block of ~/.jcode/prompt-overlay.md, saying to run the guide | None for one session; the "$ENOWX_BIN" commands | By running "$ENOWX_BIN" guide | the preset tables above; session flags not re-read | Not checked |
Nothing here writes an agent’s settings file. A block in an instructions file is the one lasting change enowX makes to a file of the user’s, kept between markers with the rest untouched; OpenCode and Kilo Code no longer need one, and a block an older enowX left in OpenCode’s file stays, harmless, until the user removes it.
Where an agent’s docs offer no way for one session, and the closest there is:
- Gemini CLI, Hermes, Cursor, Muse, OpenClaw: MCP servers only in a settings file of the user’s (
~/.gemini/settings.json,~/.hermes/config.yaml,mcp.json,~/.config/muse/settings.json), which enowX doesn’t change. Closest: the"$ENOWX_BIN"commands, or the user adding"$ENOWX_BIN" mcpthere themselves. - Cursor, Hermes, OpenClaw, Kimi, OpenCode 2: instructions only from the project’s folder or a file of the user’s identity (
SOUL.md). Writing into either would change what isn’t enowX’s. Closest: the line after the first prompt. - Trae, DeepSeek Harness, Codebuff, Freebuff: their documentation couldn’t be read here. They keep the line after the first prompt until it can.
Helpers end by themselves
Sessions enowX starts for one piece of work end when it does, without the user asking, and leave the session lists; what they made stays where it belongs. Each host’s daemon sees to its own (daemon/helpers.go).
| Session | Ends | What stays |
|---|---|---|
| A design reviewer | once its verdict is in and its turn is over | the verdict, on the run |
| A region’s unslop agent | once it says its part is done and its turn is over | the design, on the canvas |
| A build’s direction | after 15 minutes unused, as it may be sent back after the comparison | its design, on the canvas |
| A Canvas page’s agent, a Notes page’s agent | after 15 minutes unused: the next message goes on with its conversation, by its ID where the agent can resume one; else a new one, with the page’s chat log | the canvas, the note, the chat log |
One at work or waiting on the user is never ended, nor one whose hooks have gone quiet, which may be either. Not helpers, and never ended by this: sessions the user starts, GOD of Agents and its workers, anything on its board, a teammate’s session, a fan-out (its results wait to be compared), pipelines and automations (the session is their result), and tabs, which end with their session. Those left from before this are cleaned up the same way, at the first look after the daemon starts.
The model a session runs on
The session list, sessions and ls show each agent session’s project, path and model. The model is what the agent writes in its transcript with each answer, looked at every few seconds, so /model, a switch, a fallback and a config all show, Claude Code’s /model at once and others with their next answer. An agent enowX reads no transcript of, or one that hasn’t answered yet, reads “unknown model”; a stopped session shows the last it said, marked “(last)”. A program started by hand in a shell tab is listed as the shell, with no model.
Skipping permission prompts
New session’s Skip permission prompts starts an agent in its mode that asks nothing. Sessions the user doesn’t start by hand follow it only where nothing would hear a prompt: an agent with no hooks (OpenCode and most others; every agent on Windows), started as GOD of Agents, its worker, or the chat of a note or a canvas (SkipUnheard). Claude Code and Codex tell enowX they are asking, so GOA’s workers of them stay as goa delegate said (--yolo), and GOA answers. goa start --yolo is the same default on the command line.
The mode is the one a session shows (“skips permission prompts”), and stays through resuming and waking. An agent with no keys for its mode (OpenCode) takes it only as it starts: switch --mode says so.
OpenCode’s mode is --auto: it approves what asks, in the session and its subagents, and paths outside the project, .env reads and repeated calls included; a deny rule of its config still stops the tool, which reports it in the session. enowX doesn’t touch that config.
When a session dies
A session that ended badly says why beside its name, in session.exitWhy and in the daemon’s log: the signal for a code above 128 (129 is a hang-up), and that it never got going when that was within five seconds. Three such endings in a row keep it from being continued for 30 seconds, so nothing restarts it in a tight loop.
Limits
Agents at once (command palette) sets how many agents may work at the same time on a host, kept by its daemon in ~/.enowx-app/settings.json. An agent session started past it is created at once, with its worktree, but shows as queued and runs nothing; the daemon starts it in that session when an agent finishes its turn (as its hooks or its screen tell), oldest first. An agent just started counts as working for 10 s, so the next one doesn’t start before it begins. Shells and custom commands are never queued. A daemon restart forgets the queue: the sessions waiting are gone.
Set time budget… (a session’s menu, or the palette) sets how long its agent may work, counting only while it works. Past it, the daemon interrupts the agent as its user would (Escape for Claude Code and Codex, Ctrl+C for the others), the session says so, and the app notifies. A new budget lifts it. The work counted starts again when the daemon restarts. Budgets are in time only: what an agent costs isn’t known for every agent (see Credits).
Credits
The daemon reads what each signed-in account has left (core/credits, credits.get) and the app shows it on the Credits page. Tokens are read when needed and sent only to the vendor that issued them; enowX never stores, logs or refreshes them, since refreshing would sign the agent out. A reading is reused for 5 minutes. All three sources are undocumented and may change; a changed answer shows as an error on the card.
| Agent | Login read | Asked |
|---|---|---|
| Claude Code | macOS keychain items Claude Code-credentials*, else ~/.claude/.credentials.json | GET api.anthropic.com/api/oauth/usage (anthropic-beta: oauth-2025-04-20) |
| Codex | $CODEX_HOME/auth.json (~/.codex) | GET chatgpt.com/backend-api/wham/usage with ChatGPT-Account-Id |
| Kiro CLI | its own | kiro-cli chat --no-interactive /usage, parsed; account from kiro-cli whoami --format json |
Caveats
- Claude Code refuses
--dangerously-skip-permissionsas root. An address without a user signs in as root, and enowX then runs its daemon, and so every session, as a regular user of its own,enowx, made the first time (or the one it ran as before), throughsu. Sign in to each agent once from a Shell session as that user. The choice is saved per host. To run as root, or as another user, pick it in Hosts › ⋯ › Edit… › Run sessions as (A regular user with its name, or root) and save: enowX connects again as it says, and keeps it on every connection after. Hosts › ⋯ › Ask which user to run as makes the next connection ask instead, listing the server’s users. Sessions started as one user stay with that user’s daemon. If you keep root, enowX reports Claude Code’s refusal to skip permission prompts instead of starting the session. - Gemini CLI enables its sandbox with
--yolo(a Docker image by default). Without Docker, setGEMINI_SANDBOX=falsein the server’s environment, or turn sandboxing off in~/.gemini/settings.json, if that is what you want. - Skipping permission prompts lets an agent run any command and edit any file the user can. Worktrees isolate files between sessions, not from the rest of the machine.
Forking a session
A session’s menu (Fork…, which warns first), enowx-app fork SESSION [PROMPT] and MCP session_fork start a new session, “NAME (fork)”, from a compacted copy of its conversation, so a long session’s context goes on fresh and the original stays. The agent copies the conversation (claude --resume ID --fork-session, codex fork ID) and /compact runs in the copy, so the old session’s history, state, branch and folder aren’t touched. It takes the same folder and branch, as the owner decided: two agents there can overwrite each other’s changes, which the dialog and the command say. A session whose agent stopped is brought back first; one working is refused until its turn ends. /compact is typed only once the copy shows its prompt, and success is read from its conversation. If it can’t start or compact, the new session goes and the error says why. Other agents answer that it isn’t supported yet.
Agents don’t move the user
What shows depends only on what the user did: a click, a key, or a click on a notification. Agents, tools, daemon events, syncs and timers change content, not where the user is, and never take the keyboard from a field. What an agent wants to show comes as a card at the window’s top right, and a click goes there: canvas open, goto and compare, creds login. browser open loads the session’s Browser and marks it. A connection dropping leaves the page and open forms in place. What needs the user’s answer and isn’t their doing (an agent’s or a daemon’s question, a prompt on a connection the app started by itself: host control, Takeover, the vault, features, hibernating, the judge, an account at its limit, a RAG offer, trusting a server, whom to run as, a passphrase, signing in) comes as a card at the window’s top centre, not a dialog. It takes no focus and blocks nothing: what the user is typing keeps every character and the keyboard, and Enter or Space approves nothing. They answer with a click, or with Tab, then Enter: the safe answer comes first, a password field waits for a click, and for its first half second a card ignores its buttons, in case a click was already on its way. One shows at a time, the oldest first, the next with controls of its own, so a second Enter answers nothing; behind a dialog the user opened it waits. In a terminal, which takes Tab for itself, the way there is a click. Past the daemon’s wait (host control, hibernating and features 5 minutes, the vault 2) the card goes and counts as refused, so a late yes runs nothing. A dialog the user opened themselves, a connection they started included, is modal and focused as ever.