CLI behavior notes

CLI Flags

Command groups that default to a nested list command still parse flags at the subcommand level. Use the explicit list form when passing list options, such as sase notify list -j, sase agent hold list -j, or sase workspace list --json. See the daily operation guide for which groups delegate to list.

sase (global)

These options are recognized only in the leading run of option tokens, before the first subcommand. They do not steal -f/-F or -p from commands such as sase bead list -f json or sase completion candidates -p PROJECT.

Moved to CLI command groups.

Moved to sase tui.

Moved to Launching the TUI.

Moved to Launch Control.

Moved to Service host initialization.

Moved to Scheduler.

Moved to Scheduler.

Moved to Scheduler.

Moved to Scheduler.

Moved to Scheduler.

Moved to Scheduler.

Moved to Scheduler.

Moved to Scheduler.

Moved to Commit workflows.

Moved to Commit workflows.

Moved to Patch Format Documentation.

Moved to Patch Format Documentation.

Moved to ProjectSpec Format.

Moved to Workspaces.

Moved to sase revert.

Moved to Patch Format Documentation.

Moved to Agent-initiated launches.

Moved to Agent workflows.

Moved to Macro CLI and editor support.

Moved to sase macro.

Moved to sase macro.

Moved to Macro CLI and editor support.

Moved to sase macro.

Moved to sase macro.

Moved to sase macro.

Moved to Macro CLI and editor support.

Moved to Initialization.

Moved to Machine initialization.

Moved to Instruction bundles.

Moved to Memory.

Moved to Memory initialization.

Moved to Initialization.

Moved to Instruction bundles.

Moved to Workspaces.

Moved to Named tools and ToolRuns.

Moved to SASE disk cleanup.

Moved to Workspaces.

Moved to Bead CLI.

Moved to Plan commands.

Moved to Diagnostics and support reports.

Moved to Diagnostics and support reports.

Moved to Feature flag configuration.

Moved to Prompt and tool configuration.

Moved to Diagnostics and support reports.

Moved to Agent output variables.

Moved to Diagnostics and support reports.

Moved to Diagnostics and support reports.

Moved to Editor Integration.

Moved to Artifact References.

Moved to Artifact References.

Moved to Command-backed interaction gates.

Moved to Sudo Requests.

Moved to Editor Integration.

Moved to sase path.

Moved to Diagnostics and support reports.

Moved to Notification CLI.

Moved to Plan commands.

Moved to Artifact References.

Moved to sase questions.

Moved to Agent sessions.

Moved to Installing & Authenticating Agent Providers.

Moved to Prompt History and Draft Recovery.

This page is a command index for the top-level sase CLI. It is meant for discovery and routing: use it to find the surface that owns a workflow, then follow the links to the detailed command, flag, or subsystem reference.

Compact sase --help lists only the common commands. Use sase --full-help (or -H) to print every command, then this page to route from a command to its owner guide. This page is a discovery index, not a dump of every flag. Compact help's one-line agent blurb says "active and recent"; default sase agent list (and bare sase agent) is running-only — add -a for recent DONE/FAILED.

When a plugin mounts commands, compact help adds a Plugin commands group after the common commands. Each row is the command name, its one-line summary, and the distribution that provides it. The group is left out when nothing is mounted. A plugin that fails to load can still appear there with its distribution's summary, so being listed does not prove that it can run. Load failures, name collisions, and shadowed names appear on sase --full-help instead, each marked ⚠, and that footer closes with a pointer to sase plugin list and the Updates tab. See Command plugins.

Current memory commands inspect, read, initialize, and audit memory; sase's TUI Memory panel can add, edit, and delete flat notes and add or delete strands, while existing strand bodies and web descriptors are edited in $EDITOR. Agents must route all memory-file changes through /sase_memory_write first.

For exhaustive flags, options, and subcommands, see the generated CLI command groups.

The root sase command accepts leading global options before the subcommand: -f/--enable-feature and -F/--disable-feature force a registered feature flag on or off for that invocation and its children, and -p/--print-command prints a shell-quoted, copyable sase ... header to stderr before running the command. The printed invocation omits only the root print switch. See the configuration reference.

_[project]: A sase project is a named unit of work registered with SASE. _[workspace]: A sase workspace is a numbered clone of a project's primary repo, managed by the workspace store and tracked in that project's registry.json. _[agent]: A sase agent is an agent session or a single agent that does not belong to a session. _[prompt]: A prompt is the text SASE hands to a provider to start an agent turn. _[macro]: A macro is a reusable prompt triggered with #name in agent prompts. _[Patch]: A Patch is SASE's local unit of change. _[bead]: A bead is one tracked work item in SASE's git-native issue tracker. _[plan]: A plan is a persisted, approved artifact recording the intent behind agent work. _[TUI]: The TUI is SASE's terminal interface for running agents and reviewing results. _[epic]: An epic is an executable multi-phase plan run with sase bead work. _[gate]: A sase gate is a durable, command-backed request for one user decision, created when work must pause for the user. _[monitor]: A sase monitor is a monitor turn that runs one long command under a detached supervisor, so the command outlives the agent that started it. *[stitch]: A stitch is the lightweight ordered change record inside a Patch's STITCHES: section.