Slash Commands Reference
agents-fleet registers 70 built-in commands plus 11 auto-discovered workflow commands (synthesized at startup from bundled workflow frontmatter). Project/user workflows may add more. Built-in source of truth: src/commands/registry.ts; workflow commands: src/skills/bundled/workflows/**. Project workflow command synthesis is trusted by default; disable it with --no-trust-project-workflows. Reload after saving or manually editing workflows. See Workflows and Crews.
Generated for agents-fleet v0.60.0 · 70 built-in + 11 workflow commands.
UI
| Command | Aliases | Description |
|---|---|---|
/help | — | Show available commands |
/docs | /doc | Browse and read the shipped fleet documentation in chat |
/clear | /cls | Clear the screen |
/version | — | Show version information |
/exit | /quit /q | Exit the CLI |
/restart | — | Restart agents-fleet in a new PowerShell window with the SAME flags + cwd + env (Windows-only in v1). The new window inherits the current shell's env, preserving FLEET_HOME, AGENTS_FLEET_TELEGRAM_TOKEN, and security flags (--yolo, --acknowledge-*) exactly. |
/copy | — | Copy last assistant message to clipboard |
/scroll | /more /less | View conversation history in a scrollable pager |
/history | — | Show conversation history (page by page) |
/compact | — | Compress conversation context |
/view | — | Switch chip-strip view, list views, or enter strip-focus mode |
/name | — | Set or view session name |
Sessions
| Command | Aliases | Description |
|---|---|---|
/sessions | — | Interactive session picker |
/resume | — | Resume a previous session |
/config | — | Show or update configuration |
/cost | — | Show accumulated token costs |
/tokens | /usage /ctx | Show token usage and context window status |
/stats | /status | Show session statistics |
/doctor | /diag | Run diagnostic checks |
/diagnose | — | Live runtime diagnostics for the coordinator (separate from /doctor which checks env) |
/stall-history | — | Show recent coordinator stall + recovery events from the intel DB (T-214) |
/model | /m | Show or switch the current model |
/models | — | Interactive model picker |
/context-tier | /context-window | View or set the context-window caps (coordinator + worker; default 200k / long_context 1M) |
/effort | — | Show or change reasoning effort level |
/plan | — | Enter or exit plan mode |
Fleet
| Command | Aliases | Description |
|---|---|---|
/workers | — | Show active workers with progress |
/stop | — | Stop a specific worker |
/send | — | Send a message to a specific agent |
/broadcast | — | Broadcast a message to all team members |
/fleet-log | /log /activity | Show agent activity log (or tail the log file) |
/pause-dispatch | /pause | Pause automatic task dispatch to workers |
/resume-dispatch | /unpause | Resume automatic task dispatch to workers |
/topology | — | View or set the messaging topology (hub, mesh, silent) |
/team | — | Team management (coordinator-managed; humans usually use /broadcast or /crew) |
/team-repo | /meta | Manage the shared team meta-repo (init/sync/push/promote/status) |
Tasks
| Command | Aliases | Description |
|---|---|---|
/root | — | Native root status and controls (native sessions only) |
/tasks | — | Show task breakdown with dependency graph |
/dod | /definition-of-done | Show Definition of Done status and verify items |
/start | /go /run | Start fleet execution of the task plan (auto-loops every 30m) |
/loop | — | Auto-execute on an interval until all tasks are complete (alias of /loop-target) |
/loops | — | List and manage active loops |
/loop-target | /auto /execute | Auto-execute on an interval until all tasks are complete |
Workflows
| Command | Aliases | Description |
|---|---|---|
/new-project | /kickoff /project | Start a guided project planning session (7 interactive phases) |
/brainstorm | /brain /bs | Adversarial multi-agent pre-feature brainstorming. Spawns 3 inquisitor explorers to grill the user with questions until consensus. |
/feature | /feat /epic | Plan a feature on an existing project, workflow-driven (brainstorm → requirements → research → design → validation → DoD → tasks) |
/compete | /race /bakeoff | Run adversarial implementation competition (parallel builds in git worktrees) |
/do | — | Plan and execute a task with DoD tracking (research → plan → execute) |
/fast-do | /quick | Quick execution — skip planning, up to 3 workers |
/workflows | — | Manage suspended workflow interrupts (list / status / resume / abort / release) |
/approve | — | Resume the suspended workflow in this cwd with decision=continue |
/reject | — | Resume the suspended workflow in this cwd with decision=abort |
/wf | — | Workflow status, pinned graphs, managed stage controls, scaffolding and registry reload |
Knowledge
| Command | Aliases | Description |
|---|---|---|
/skills | — | List available roles, atomic skills, and workflows (or migrate v1) |
/skill | /sk | Create or list skills |
/skills-migrate | — | Migrate v1 .md skill/crew files to v2 (.role.md / .crew.md) |
/crews | — | List available crews (v2 roster + workflow) |
/crew | — | Activate, generate, or manage crews (/crew create is LEGACY/DEPRECATED v1) |
/learn | /intelligence | Review fleet intelligence learnings, suggestions, and memory |
/experiment | /exp | Define, run, and report A/B experiments over skills/roles/crews |
/fleet-intel | /intel | View fleet intelligence insights from past sessions |
/mcp | — | Manage MCP servers |
/context-status | /init-status | Show project context status (files generated by /init). Alias: /init-status (deprecated, removal next major) |
/context-scopes | /init-scopes | List available context scopes from .fleet/context/scopes.json. Alias: /init-scopes (deprecated, removal next major) |
/context-load | /init-load | Load a context scope into the current conversation. Alias: /init-load (deprecated, removal next major) |
Git
| Command | Aliases | Description |
|---|---|---|
/diff | — | Show git diff of current changes |
/commit | — | Create a git commit (delegates to coordinator) |
/worktree | /wt | Manage git worktrees for worker isolation |
Telegram
| Command | Aliases | Description |
|---|---|---|
/bot-set-token | — | Persist Telegram bot token to ~/.fleet/telegram.json (mode 0600). The AGENTS_FLEET_TELEGRAM_TOKEN env var always wins over this file. |
/bot-clear-token | — | Remove Telegram bot token from ~/.fleet/telegram.json. Idempotent. Does not affect the AGENTS_FLEET_TELEGRAM_TOKEN env var. |
Workflow Commands (auto-discovered)
| Command | Aliases | Description |
|---|---|---|
/bug-autopilot | /bugfix-autopilot | End-to-end bug-fix autopilot: reproduce → fix → regression-test → code-review loop → open PR → wait for human approval → iterate on feedback → merge. |
/code-review | /review /cr | Run comprehensive multi-agent code review |
/code-review-autopilot | /cr-auto /review-loop | Iterative code-review auto-pilot: review → triage → fix → validate, looping until convergence; optional PR handoff via --ship. Pass --scope=full to audit the whole codebase instead of a diff. |
/fixer-loop | — | Auto-pilot loop that reviews, triages, fixes, and verifies. Iterates until convergence or budget exhausted. |
/full-review | /cr-full /full-cr | Full-codebase report-only review (no fixes): audits the ENTIRE tree via the empty-tree..HEAD range with 5 parallel reviewers and writes CODE_REVIEW.md. Nothing is modified. |
/github-issue-worker-autopilot | — | GitHub-issues-driven autopilot: triage open issues, fix, validate with tests, generate proof artifacts, and ship as a draft PR. |
/init | /investigate | Workflow-driven /init — parallel investigators + critic + synthesizer |
/research | /investigate-topic /deep-dive | Adversarial deep research on a topic (parallel explorers + critic) |
/security-autopilot | /sec-audit /security-audit | Defensive application-security audit autopilot: recon → hunt (per-class fan-out) → triage → PoC → fix → verify → report. Static analysis + local sandboxed PoCs only; never touches live/third-party systems. Pass --ship to open a PR with the fixes; default writes SUMMARY.md + report.md only. |
/security-binary-autopilot | /binary-autopilot /sec-binary | Binary-analysis autopilot: target recon → static RE + patch-diff → coverage-guided fuzzing in ISOLATED-DISPOSABLE Azure VMs → crash triage + exploitability + minimal impact PoC → MSRC-format report → disclosure package. Authorized-scope only; isolated/disposable VMs; coordinated disclosure via MSRC only; no weaponization. |
/security-disclosure-autopilot | /sec-disclose /msrc-autopilot | Coordinated-disclosure autopilot: recon → scan → triage → local PoC → ISOLATED-DISPOSABLE Azure-VM detonation + evidence capture → MSRC-format report → optional fix → disclosure package. Authorized-scope only; MSRC coordinated disclosure only; isolated/disposable VMs (no prod/third-party, auto-teardown); evidence integrity (hash+timestamp). |