Start an input with / in the TUI to trigger a command and get an autocomplete menu. The 50+ built-in commands are organised below; commands loaded from Skills and Plugins also appear in the menu automatically.
Core
Command
Purpose
/login
Recommended — one command runs AtomGit OAuth + claims CodingPlan free tokens + auto-configures a provider from the granted model list. The lowest-friction entry point for first-time users; re-running after you're already signed in idempotently re-syncs the model list. As of v4.25.0 /codingplan has been folded into /login; the standalone entry has been removed
/resume
Open the session picker to restore any previously persisted session (messages, directory, and model state)
/session
Start a fresh, clean session
/bg
Send the current session to the background and open a new foreground; subcommands: /bg list, /bg <N>, /bg drop <N>, /bg help. See Background sessions
/background <task>
Compatibility entry: start a one-shot task in a /bg slot (details)
/rename <new-name>
Rename the current session (changes the display name in the /resume picker)
/provider
Open the provider manager: add / edit / remove / switch
/model
Switch models within the current provider, or jump across providers
/cd
Change working directory and write it back as default_workdir. You can also just type cd /path (no slash prefix)
Tools & utilities
Command
Purpose
/view <filepath>
Open a read-only overlay to view a file's content (supports arrow keys, PageUp/Down, g/G to jump to top/bottom)
/undo · /undo N
Roll conversation memory back to before the last turn (or turn N) and restore that prompt into the input box; rewinds memory only — does not revert files on disk
/diff
Show the git diff of uncommitted changes in the working directory
/review
Code review the current changes: /review reviews uncommitted changes, /review staged the staged diff, /review <base> against a base ref
/paste
Attach an image from the clipboard (Windows fallback for when Ctrl+V is captured by the terminal)
/cost
Show output tokens for the current session. APIs without usage reporting are estimated automatically
/context
Show this turn's context budget breakdown: system prompt, tool defs, cold-zone compaction, total messages, and context-window usage
/compact
Compact history: summarise earlier messages to free up context budget
/clear
Clear the current session's messages (working directory and model are kept)
/init
Scan the working directory and generate / refresh the .atomcode.md project instructions file — covering build / test commands, tech-stack summary, layout, etc.; injected as system prompt on subsequent launches
/background <task>
Dispatch a task to an isolated background agent (read-only-leaning tool subset) without polluting the main conversation. Useful for "go check X on the side" sort of light exploration. See Background sessions
/worktree <subcommand>
Git worktree isolation: create a new branch with its own worktree, list existing worktrees, done squash worktree changes back to the main branch, cleanup remove finished worktrees
/issue
Interactive wizard: file a new issue against the AtomGit repository for the current git repo (requires OAuth login; cwd must be a clone of an atomgit.com repository)
/todo
Reprint the current todo list — derived from the session transcript (locates the most recent todowrite tool call and re-renders it), with "in-progress / done" status markers. The list is stateless (nothing extra is written to disk); the model maintains it during long tasks and you can run this anytime to check progress
/copy
Copy a code block from the last reply to the clipboard: /copy copies the only block, /copy N the N-th, /copy all every code block, /copy msg the whole reply as raw markdown
/save
Export the current conversation to a markdown file: /save uses an auto-generated filename, /save <filename> a name you choose
Conversation modes & thinking
Command
Purpose
/plan
Switch to Plan mode: read-only exploration. The model can call read_file / grep / list_directory and other non-writing tools, but edit_file / bash are blocked. Useful for getting alignment before action
/build
Switch back to Build mode (the default): all tools available — read, write, execute. /plan and /build are freely interchangeable
/goal <text>
Set a completion goal and let the agent run an autonomous loop — turn after turn — until the goal is met. /goal (no args) shows the current goal and round count; /goal clear stops it
/loop <interval> <prompt or /command>
Repeat a prompt or slash command on a fixed interval. e.g. /loop 5m /diff runs /diff every 5 minutes; /loop 30s check the build re-sends that prompt every 30 seconds. Interval units are s/m/h, range 10s–24h
/loop <prompt>
With no interval, enters self-paced mode: the task is handed to the model, which decides when to run the next round itself — good for "keep at this until it converges" work that doesn't map onto a fixed period
/loop · /loop stop
/loop (no args) shows the current loop status; /loop stop (or off / clear / cancel) stops it. /loop and /goal are mutually exclusive — setting one automatically cancels the other
/think on / off
Toggle extended thinking (for supported models — Claude / DeepSeek-R1 / GLM-4.5 / …). When on, the model surfaces its reasoning at the cost of latency and tokens
/think budget <N>
Cap the thinking token budget (Claude family); controls reasoning length
/effort <high|max|off>
DeepSeek reasoning-effort control — trade latency/tokens for deeper reasoning on DeepSeek models
Persistent memory
Command
Purpose
/remember <content>
Write to project-scoped memory (default scope, bound to the current working directory)
/remember --global <content>
Write to global memory (shared across all projects)
/forget <keyword>
Delete every entry in global + project memory matching the keyword (case-insensitive)
/memory
Show all active memories, grouped by [Global] / [Project]
On first run, install the bundled atomcode-automation-recommender skill into ~/.atomcode/skills/, append .atomcode/local/ to project .gitignore, and write .atomcode/setup-state.json (signals hash + atomcode version + installed list) under a project-level lock. Then invoke the recommender skill — it scans the project (languages, frameworks, hooks already in use), searches the web, and proposes additional atomcode skills to install for this codebase. Subsequent runs skip the seed install and re-invoke the skill directly. Extra text after the command is forwarded to the skill as a steering hint, e.g. /setup focus on testing. The CLI form atomcode setup --force forces a clean reinstall of seed files even when their content hash matches
/skills
Browse loaded skills (project- and user-level). Each skill also appears as a standalone slash command in the menu — trigger with /<skill-name>
/plugin
Open the interactive plugin manager — browse marketplaces, install/uninstall plugins, add/remove marketplaces from one screen
/plugin marketplace add|remove|update|list
Manage marketplace registrations (add clones a git repo, remove deletes, update pulls latest, list shows all)
/plugin install <plugin>@<marketplace>
Install a plugin from the named marketplace
/plugin uninstall <plugin>@<marketplace>
Uninstall an installed plugin (the marketplace registration is kept)
/plugin list
List locally installed plugins
/plugin reload
Reload all plugins (re-scan disk, refresh skill/hook registration)
Plugins can register their own slash commands. For example, the official channel plugin adds /wechat (shows the AtomCode WeChat community group QR code):
Launch the browser interface and open it (binds 127.0.0.1:13457 by default — local only). The current TUI session is attached to live sync automatically
/webui --host <addr>
Bind the server to a given address; /webui lan equals --host 0.0.0.0 (exposes it to the LAN). Pair with a 蒲公英 virtual IP for remote access — see Remote Access
/webui stop
Stop the webui server
/sync
Attach the current TUI to a running webui session (run /webui first). Both ends sync live in both directions; multiple browsers / terminals can watch the same session
/sync off
Leave sync and return to a standalone session
/app
Expose the current session to the mobile App via the official relay: a QR code is printed right in the terminal, scan it with the App to pair, then view and drive this conversation live from your phone (same source as /webui — one shared session, two-way live sync; the difference is no browser, and it goes over the relay rather than the LAN). Requires /login first
/app stop
Stop App remote access, disconnect the relay, and return to a local session
Show login status, current provider, model, context budget, CodingPlan usage and reset time
/whoami
Show the username / email of the current AtomGit-logged-in user
/config
Show the path of ~/.atomcode/config.toml
/reload
Hot-reload ~/.atomcode/config.toml from disk — external edits (or changes from another terminal's /login) take effect without restarting atomcode
/proxy
Switch outbound proxy mode: follow the system proxy (default) / force a specific proxy / connect directly with no proxy. For corporate proxy networks or when you need to force a proxy or force a direct connection; the choice is written back to config
/language
Switch UI language: auto-detect (LC_ALL / LANG), English, or Simplified Chinese. Takes effect immediately and is written back to ~/.atomcode/config.toml
/welcome
Re-open the 3-step first-run wizard (welcome → language → setup). Non-empty sessions are confirmed with a y/N before clearing the screen. Both language and default onboarding path can be revisited here
/logout
Clear the AtomGit OAuth token
/upgrade
Auto-upgrade to the latest version; /upgrade rollback reverts to the previous version
/guide
Built-in onboarding guide: /guide lists topics you can ask about (quickstart, switch model, MCP, Skills, memory, background tasks, context, keybindings, config); /guide <topic> explains it right in the chat (first run auto-installs the atomcode-skills plugin)
/help
List every available slash command
/keys
Show the keyboard-shortcut reference (grouped by input / history / session / modal navigation, with per-terminal compatibility notes for Shift+Enter and Alt+Enter). See Keybindings
/quit · /exit
Exit atomcode (or hit Ctrl+C twice)
Tips
Autocomplete — typing / pops up the menu immediately; use ↑↓ to navigate, Tab / Enter to confirm.
Fuzzy match — completion supports substring matching, e.g. /prov hits /provider.
Interrupt the model — while the model is streaming, press Esc to interrupt; you can then enter a new command or prompt.
Skills appear in the menu — once you add your own commands under Skills, they show up in the menu in the same format.
Typical workflows
First launch — one-click onboarding
> /login
✔ Logged in as alice (alice, alice@example.com)
✔ CodingPlan claimed — CodingPlan Free · expires 2026-05-22 (29d / 30d)
✔ 3 models registered as AtomGit-* providers
✔ Default provider set to AtomGit-GLM
> hello
Check cost before wrapping up
> refactor src/db to use a connection pool
... (AI works)
> /cost
Session token usage
- Total output tokens: 8342
- Current turn tokens: 2156
- Context: 42K / 128K
Rewind and re-ask when the answer goes sideways
> add JSDoc to every function
... (the reply went off the rails)
> /undo
Rolled back to turn 3 of 3.
⚠ Only conversation memory was rewound; files on disk were not restored. Revert code manually or check /diff.
(your last prompt is back in the input box — edit and resend)
Swap the model when it underperforms
> /model
> (pick claude-opus-4-6 from the popup)
> try again — this time preserve existing comments
Next steps
Keybindings — pair commands with keybindings to double your speed
Sessions & Undo — full behaviour of /resume, /undo, /compact
