Slash Commands

Slash commands are built-in commands for Pythinker Code, used to control sessions, configuration, and debugging. Enter a command starting with / in the input box to trigger.

Shell mode

Many slash commands are also available in shell mode, including /help, /exit, /version, /agents, /editor, /theme, /changelog, /feedback, /report-error, /export, /import, /task, /settings, /statusline, /restore, /trust, /worklog, /context, /tools, /accessibility, /keys, /tui, /thinking, and /hooks.

Help and info

/help

Display help information. Shows keyboard shortcuts, all available slash commands, and loaded skills in a fullscreen pager. Press q to exit.

Aliases: /h, /?

/version

Display Pythinker Code version number.

/changelog

Display the changelog for recent versions.

Alias: /release-notes

/feedback

Submit feedback to help improve Pythinker Code. You will be prompted to enter your feedback and submit it. If the network request fails or times out, the command automatically falls back to opening the GitHub Issues page.

/report-error

Submit a report about an error you hit, with a snapshot of recent failures. The runtime keeps a process-local ring buffer of the last 10 handled errors; this command prints them, lets you add a free-form comment, and submits both to the feedback endpoint. If submission fails, it falls back to opening the GitHub Issues page. See Telemetry & error reporting for details.

Aliases: /report

/agents

List the available subagent types, showing each agent's name, when to use it, its default model, and its tool posture.

/prompt-manifest

Show the latest request-assembly status for the current session. The output includes opaque, stable fragment identifiers, admission outcomes, and token estimates. It never includes prompt content, user content, raw source names, raw file paths, credentials, or stack traces. Before the first assembled request, the command reports that no manifest is available.

Account and configuration

/login

Log in or configure an API platform. After execution, first select a platform:

• Pythinker: Automatically opens a browser for OAuth authorization
• Other platforms: Enter an API key, then select an available model

After configuration, settings are automatically saved to ~/.pythinker/config.toml and reloaded. See Providers for details.

Alias: /setup

TIP

This command is only available when using the default configuration file. If a configuration was specified via --config or --config-file, this command cannot be used.

/logout

Log out from the current platform. This clears stored credentials and removes related configuration from the config file. After logout, Pythinker Code will automatically reload the configuration.

/model

Switch models and thinking mode.

This command first refreshes the available models list from the API platform. When called without arguments, displays an interactive selection interface where you first select a model, then choose whether to enable thinking mode (if the model supports it).

After selection, Pythinker Code will automatically update the configuration file and reload.

TIP

This command is only available when using the default configuration file. If a configuration was specified via --config or --config-file, this command cannot be used.

/editor

Set the external editor. When called without arguments, displays an interactive selection interface; you can also specify the editor command directly, e.g., /editor vim. After configuration, pressing Ctrl-O will open this editor to edit the current input content. See Keyboard shortcuts for details.

/theme

Switch the terminal color theme. Pythinker Code provides dark and light color palettes, defaulting to dark.

Usage:

• /theme: Show the current theme
• /theme dark: Switch to dark theme
• /theme light: Switch to light theme

After switching, the configuration is saved to config.toml and the shell reloads automatically. The light theme adjusts colors for diff highlights, the task browser, the prompt completion menu, the bottom toolbar, and MCP status indicators to work well on light terminal backgrounds. You can also set theme = "light" directly in your config file — see Config files.

Alias: /color

/statusline

Customize the status line (the footer under the prompt): choose which segments are shown, adjust the footer's visual style, and optionally add an external status command.

Usage:

• /statusline: Open the interactive status line settings menu (falls back to the static configuration table while a turn is streaming)
• /statusline show (aliases list, view): Show the current status line configuration table
• /statusline on / /statusline off: Enable or disable the customizable status line (off renders the stock footer)
• /statusline segments <id,...>: Choose the segments to show, e.g. /statusline segments cwd,git,model. Run /statusline segments with no ids to list every segment id, its zone, and its current state
• /statusline style fancy / /statusline style plain: Set the footer visual style — fancy renders colors, separators, and the context bar; plain keeps a monochrome text-only footer
• /statusline bar-width <4-20>: Set the width (in cells) of the context progress bar
• /statusline budget <usd> / /statusline budget none: Set or clear an optional session cost budget in USD; when set, the cost segment renders $spent/$budget
• /statusline command <argv...>: Set an external command whose first stdout line is shown in the footer (refreshed periodically; run without a shell; killed after command_timeout_ms). Setting a command also adds the command segment if not already shown
• /statusline command none: Clear the external command

Available segment ids: spinner, model, cost, speed, effort, cwd, git, diff, flags, context, tokens, elapsed, limits, clock, command. Settings persist under [tui.statusline] in config.toml; PYTHINKER_STATUSLINE=0 disables the status line for a session. The footer style defaults to fancy.

/settings

Open the interactive settings panel. Without arguments it opens the panel; the read-only and quick-toggle forms are also available.

Usage:

• /settings: Open the interactive settings panel
• /settings show (aliases list, view): Print a read-only settings table (theme, TUI style, default model, telemetry, default thinking, turn recaps, default YOLO/plan mode, config file path)
• /settings recaps on / /settings recaps off: Toggle per-turn recaps

Alias: /config

/tui

Show or set the TUI rendering style.

Usage:

• /tui: Show the current TUI style
• /tui card: Use the card style (highlighted user messages and bordered tool cards)
• /tui pythinker: Use the legacy worklog-based rendering

The setting is persisted to config.toml (under [tui]) and the shell reloads. You can also override at runtime with PYTHINKER_TUI_STYLE=pythinker.

/thinking

Switch the thinking effort level via an interactive picker.

/keys

List the keyboard shortcuts from the active semantic keymap. See Keyboard shortcuts for the full reference.

Alias: /keybindings

/accessibility

Show or update accessibility and plain-output preferences. Settings persist with the session state.

Usage:

• /accessibility: Show the current preferences
• /accessibility plain / /accessibility rich: Toggle plain (text-only) output (on / off are accepted aliases)
• /accessibility no-animation / /accessibility animation: Disable or enable animations
• /accessibility ascii / /accessibility unicode: Choose ASCII or Unicode symbols

Alias: /a11y

/trust

Show or update the workspace trust safe mode for the current session.

Usage:

• /trust: Show the current trust and safe-mode state
• /trust on: Trust the workspace and disable safe mode (aliases yes, trust)
• /trust off: Untrust the workspace, enable safe mode, and disable auto-approval (aliases no, untrust, safe)

/stats

Show the usage statistics dashboard (tokens and cost by provider/model), read from ~/.pythinker/sessions/.

Alias: /history

/update

Check for and optionally install the latest Pythinker Code version.

Alias: /upgrade

Running /update opens a menu: Check for updates now (the default, so a bare /update + Enter checks immediately) or Auto-update on startup, which shows the current state and jumps to the toggle.

Use /update auto on or /update auto off to turn silent startup auto-updates on or off (persisted to the auto_update config field); /update auto with no argument opens an interactive On/Off picker, with the cursor defaulted to the current setting. When an external override is active — the PYTHINKER_CLI_NO_AUTO_UPDATE kill-switch or a source checkout — it is surfaced as the reason and outranks the setting, and /update auto reports that read-only state instead of opening the picker. The same toggle is available in /settings, and pythinker info reports the auto-update status.

/reload

Reload the configuration file without exiting Pythinker Code.

/debug

Display debug information for the current context, including:

• Number of messages and tokens
• Number of checkpoints
• Complete message history

Debug information is displayed in a pager, press q to exit.

/usage

Display API usage and quota information for the current model's provider, showing usage with progress bars and remaining percentages.

Usage:

• /usage: Show usage for the active model's provider (falls back to all providers when no model is active)
• /usage all: Show usage for every configured provider
• /usage <provider-key>: Show usage for a specific provider
• /usage --json: Output the report as JSON

Aliases: /status, /cost

/mcp

Display currently connected MCP servers and loaded tools. See Model Context Protocol for details.

Output includes:

• Server connection status (green indicates connected)
• List of tools provided by each server

/hooks

Display currently configured hooks. See Hooks for details.

Output includes:

• Event types and counts of configured hooks
• Help message (if no hooks are configured)

/context

Show the current context, checkpoint, and compaction status: context tokens, context window size, usage percentage, number of checkpoints, plan-mode state, and the context file path.

/tools

List the tools available to the agent along with the active permission posture (the permission profile name, whether file and shell mutations are allowed, and each tool's description). Append audit (/tools audit) for a note on how external MCP/wire/plugin tools are gated in read-only, plan, review, and verify profiles.

Benchmarks

/benchmark

Run deterministic local benchmark tasks through the active Pythinker session. The default suite is pythinker-core, which materializes a throwaway workspace, asks the agent to fix the task, runs the task's verification command, and writes replayable artifacts under the benchmark output directory.

Usage:

• /benchmark start [--model <model-key>] [--task <task-id> | --suite <suite-name>]
• /benchmark estimate [--model <model-key>] [--task <task-id> | --suite <suite-name>]
• /benchmark compare --models <model-a,model-b> [--task <task-id> | --suite <suite-name>] [--repeat <n>]
• /benchmark list
• /benchmark show <run-id>
• /benchmark report [--suite <suite-name>]
• /benchmark export [--suite <suite-name>] [--format json|csv] [--output <path>]
• /benchmark discover --source <allowlisted> --difficulty hard --limit 5 [--output <path.jsonl>]
• /benchmark swe --dataset <path.jsonl> --trusted-dataset true [--instance <instance-id>]

Namespaced aliases are also registered: /benchmark:start, /benchmark:all, /benchmark:estimate, /benchmark:list, /benchmark:show, /benchmark:report, /benchmark:compare, and /benchmark:swe. /benchmark export and /benchmark discover do not have namespaced aliases.

WARNING

/benchmark:swe executes verification commands from a local JSONL dataset. Use it only with trusted local fixture datasets and pass --trusted-dataset true explicitly.

/benchmark discover --output <path.jsonl> writes provisional quiz-fixture JSONL records with verification.type set to answer_contains, trusted: false, and an empty workspace.files object. Review and convert them offline before using /benchmark:swe.

See Pythinker Benchmark for task schema, artifact layout, and implementation boundaries.

Session management

/new

Create a new session and switch to it immediately, without exiting Pythinker Code. If the current session has no content, the empty session directory is automatically cleaned up.

/sessions

List all sessions in the current working directory, allowing switching to other sessions.

Aliases: /resume, /session

Use arrow keys to select a session, press Enter to confirm switch, press Ctrl-C to cancel. Press Ctrl-A to toggle between showing sessions for the current directory only or across all directories.

/title

View or set the current session title. The configured title is shown in the /sessions list, making it easier to identify and find sessions.

Alias: /rename

Usage:

• /title: Show the current session title
• /title <text>: Set the session title (max 200 characters)

After the first conversation turn, the title is automatically derived from the user message; once manually set with this command, auto-generation will no longer overwrite it.

/undo

Roll back to a previous turn and retry. An interactive selector shows all historical turns with the user message (truncated to 80 characters). After selecting a turn, Pythinker Code forks a new session containing all conversation history before that turn and pre-fills the selected turn's user message into the input box for re-editing. The original session is always preserved.

Use arrow keys to navigate, Enter to confirm, Ctrl-C to cancel.

Use case

When the API returns a truncated or malformed response that breaks the session, use /undo to roll back to a turn before the problem and retry without abandoning the entire session.

/fork

Fork a new session from the current one, copying the entire conversation history. The original session remains unchanged, and the new session becomes the active session. Useful when you want to branch out and try a different direction from the current state.

/export

Export the current session context to a Markdown file for archiving or sharing.

Usage:

• /export: Export to the current working directory with an auto-generated filename (format: pythinker-export-<first 8 chars of session ID>-<timestamp>.md)
• /export <path>: Export to the specified path. If the path is a directory, the filename is auto-generated; if it is a file path, the content is written directly to that file

The exported file includes:

• Session metadata (session ID, export time, working directory, message count, token count)
• Conversation overview (topic, number of turns, tool call count)
• Complete conversation history organized by turns, including user messages, AI responses, tool calls, and tool results

/import

Import context from a file or another session into the current session. The imported content is appended as reference context, and the AI can use this information to inform subsequent interactions.

Usage:

• /import <file_path>: Import from a file. Supports common text-based formats such as Markdown, plain text, source code, and configuration files; binary files (e.g., images, PDFs, archives) are not supported
• /import <session_id>: Import from the specified session ID. Cannot import the current session into itself

/clear

Clear the current session's context and start a new conversation.

Alias: /reset

/compact

Manually compact the context to reduce token usage. You can append custom instructions after the command to tell the AI which information to prioritize preserving during compaction, e.g., /compact preserve database-related discussions.

When the context is too long, Pythinker Code will automatically trigger compaction. This command allows manually triggering the compaction process.

/restore

List or restore file mutation checkpoints recorded during the session. Each checkpoint captures a file before a tool modified or created it.

Usage:

• /restore: List recent restore points (ID, tool, path, and whether the file was modified or created)
• /restore <id>: Restore the file captured by the given restore point
• /restore latest: Restore the most recent restore point

Alias: /rewind-files

/worklog

Show a compact session activity timeline: a count of wire signal types seen this session, the most recent signals, and recent file restore points.

/recap

Recap recent Pythinker sessions.

Usage:

• /recap: Recap recent sessions
• /recap <period>: Recap a specific period — today, yesterday, week, or a YYYY-MM-DD date

/memory

Show the project memory, or manage the approval-gated memory inbox.

Usage:

• /memory: Print the current project memory snapshot
• /memory inbox: List staged memory inbox candidates (requires memory.consolidation = true in your config)
• /memory inbox scan: Generate inbox candidates from the session
• /memory inbox approve <id>: Approve a staged candidate
• /memory inbox reject <id>: Reject a staged candidate

Alias: /mem

Skills

/skill:<name>

Load a specific skill, sending the SKILL.md content to the Agent as a prompt. This command works for both standard skills and flow skills.

For example:

• /skill:code-style: Load code style guidelines
• /skill:pptx: Load PPT creation workflow
• /skill:git-commits fix user login issue: Load the skill with an additional task description

You can append additional text after the command, which will be added to the skill prompt. See Agent Skills for details.

TIP

Flow skills can also be invoked via /skill:<name>, which loads the content as a standard skill without automatically executing the flow. To execute the flow, use /flow:<name> instead.

/flow:<name>

Execute a specific flow skill. Flow skills embed an Agent Flow diagram in SKILL.md. After execution, the Agent will start from the BEGIN node and process each node according to the flow diagram definition until reaching the END node.

For example:

• /flow:code-review: Execute code review workflow
• /flow:release: Execute release workflow

TIP

Flow skills can also be invoked via /skill:<name>, which loads the content as a standard skill without automatically executing the flow.

See Agent Skills for details.

Workspace

/add-dir

Add an additional directory to the workspace scope. Once added, the directory is accessible to all file tools (ReadFile, WriteFile, Glob, Grep, StrReplaceFile, etc.) and its directory listing is shown in the system prompt. Added directories are persisted with the session state and automatically restored when resuming.

Usage:

• /add-dir <path>: Add the specified directory to the workspace
• /add-dir: Without arguments, list already added additional directories

TIP

Directories already within the working directory do not need to be added, as they are already accessible. You can also add directories at startup via the --add-dir option. See pythinker command for details.

Others

/btw

Ask a quick side question without interrupting the main conversation. Available both when idle and during streaming.

Usage: /btw <question>

The side question runs in an isolated context: it sees the conversation history but does not modify it. Tool calls are disabled — the response is text-only, based on the model's existing knowledge of the conversation.

During streaming, the response appears in a scrollable modal panel overlaying the prompt area. Use ↑/↓ to scroll, Escape to dismiss.

TIP

This command is only available in interactive shell mode. Wire and ACP clients can use the BtwBegin/BtwEnd wire events with the run_side_question() API.

/init

Analyze the current project and generate an AGENTS.md file.

This command starts a temporary sub-session to analyze the codebase structure and generate a project description document, helping the Agent better understand the project.

/plan

Toggle plan mode. In plan mode, the AI can only use read-only tools to explore the codebase, writing an implementation plan to a plan file and submitting it for your approval. See Plan mode for details.

Usage:

• /plan: Toggle plan mode
• /plan on: Enable plan mode
• /plan off: Disable plan mode
• /plan view: View the current plan content
• /plan clear: Clear the current plan file

When plan mode is enabled, the prompt changes to 📋 and a blue plan badge appears in the status bar.

/goal

Set a thread goal the agent pursues across turns until it is verifiably complete. The objective persists in the session, is re-injected as a continuation reminder on later turns, and survives context compaction. The agent derives concrete success criteria up front, refuses to shrink scope to an easier task, and only marks completion through the UpdateGoal tool after an evidence-based completion audit (or blocked after a strict blocked audit) — you then confirm with /goal clear or reactivate with /goal resume.

Usage:

• /goal <objective>: Set (or replace) the thread goal and start working toward it
• /goal or /goal view: Show the current goal and its status
• /goal pause: Keep the goal but stop pursuing it
• /goal resume: Resume a paused, completed, or blocked goal
• /goal clear: Remove the goal (also how you confirm completion)

With goal.auto_continue = true in the config, the agent automatically starts follow-up turns toward the active goal after each of your messages (up to goal.max_continuations), stopping as soon as the goal is marked complete or blocked.

/best-practices

Inject the full engineering best-practices profile (operating principles, context gathering, scoping and assumptions, design and implementation, code-change discipline, version-control safety, testing strategy, debugging methodology, security and secrets, agent operational discipline, subagent orchestration, todo hygiene, progress updates, verification before done, final-answer style) into the session context. The guidance applies for the rest of the session without consuming a turn.

A condensed subset of this profile is always active in the default system prompt — every agent role inherits it without running the command. /best-practices layers the full, expanded rules on top for sessions that need the complete profile.

Usage:

• /best-practices: Inject the full guidance
• /best-practices <section>: Inject a single section, e.g. /best-practices testing or /best-practices debugging
• Alias: /bp

/learn

Review the session for reusable lessons — user corrections, non-obvious error resolutions, workarounds, conventions discovered the hard way — and persist them to the per-project memory store (and the repo's lessons file when one exists). Lessons are distilled as trigger rules ("when X, do Y"), one pattern per entry; trivia and one-time issues are skipped.

Usage:

• /learn: Review the whole session
• /learn <focus>: Steer extraction toward a specific mistake or topic, e.g. /learn the polling mistake

/task

Open the interactive task browser to view, monitor, and manage background tasks.

Alias: /tasks

The task browser is a three-column TUI:

• Left column: Task list showing task ID, status, and description
• Middle column: Detailed information for the selected task, including ID, status, description, timestamps, exit code, etc.
• Right column: Output preview showing the last few lines

Supported keyboard shortcuts:

Shortcut	Action
Enter / O	View the selected task's full output in a pager
S	Request to stop the selected task (requires confirmation)
Tab	Toggle filter mode (all / active tasks only)
R	Refresh the task list
Q / Esc	Exit the browser

The task browser automatically refreshes every second, showing real-time task status changes.

TIP

Background tasks are started by the AI using the Shell tool with run_in_background=true. The system automatically notifies the AI when background tasks complete.

/yolo

Toggle YOLO mode. When enabled, permission approvals are dangerously skipped — all tool calls are automatically approved and a yellow YOLO badge appears in the status bar; enter the command again to disable. YOLO only removes approval friction — the agent can still reach you via AskUserQuestion. /yolo and /auto are independent.

Note

YOLO mode dangerously skips all permission approvals. Make sure you understand the potential risks.

/auto

Toggle auto mode (no user present). When enabled, auto mode auto-approves all tool calls and additionally auto-dismisses any AskUserQuestion the agent sends — so the agent makes its own judgment instead of waiting for a reply that will not come. An orange auto badge appears in the status bar independently of the YOLO badge; enter the command again to disable.

Note

Auto mode skips all approval confirmations and removes the clarifying-question safety net. Only use when you genuinely cannot be at the terminal.

/web

Switch to Web UI. Pythinker Code will start a Web UI server and open the current session in your browser, allowing you to continue the conversation in the Web UI. See Web UI for details.

/reports

Open session reports in the Agent Tracing Visualizer (alias: /dashboard). Pythinker Code will start the visualizer server and open the current session's tracing view in the browser, where you can inspect Wire event timelines, context messages, and usage statistics. See Agent Tracing Visualizer for details.

Command completion

After typing / in the input box, a list of available commands is automatically displayed. Continue typing to filter commands with fuzzy matching support, press Enter to select.

For example, typing /ses will match /sessions, and /clog will match /changelog. Command aliases are also supported, such as typing /h to match /help.