Shell commands

Start the shell with opensre (needs a real terminal). Type a /command, or describe what you want in plain language.

opensre
/help

When you type / and browse with the arrow keys, the hint line above the prompt shows the highlighted command’s description.

Confirmation prompts come from /auto (tool-approval autonomy) and from elevated slash commands. Default /auto is high (alpha: no tool prompts). /trust on skips approval prompts for the rest of the session. Outside a TTY, actions that would ask are blocked.

How the REPL works

Input type	What happens
Slash command (`/status`)	Routed through the action agent and executed via `slash_invoke`
Plain language (`verify datadog`)	Routed by the action agent to slash commands, tool calls, or doc-grounded answers
Pasted alert JSON/text	The agent triages it in chat, calling integration tools as needed
Shell one-liner (`kubectl get pods`)	Executed through shell policy when the action agent selects a shell action

TTY vs non-TTY: Interactive menus, confirmations, and onboarding wizards need a real terminal. Piping input or running in CI is non-interactive — prefer explicit CLI commands outside the REPL for automation. Unknown commands: Typos suggest the closest registered command (Did you mean /integrations?). Run /help for the authoritative list — it always matches your installed OpenSRE version. Keyboard shortcuts:

Key	Effect
Up/Down	Recall persisted command history (when enabled); during `/` completion browse, preview the highlighted command description in the hint line above the prompt
Ctrl+C once	Cancel in-flight streaming work or interrupt the current prompt
Ctrl+C twice within 2s	Exit the REPL (prints `/resume` hint)
Ctrl+D	Exit when the prompt is empty (same resume hint as `/exit`)

Every launch starts guided onboarding and asks which demo to run. The four choices cover repository analysis, recurring CI/CD checks, the upcoming managed service, and Slack setup. Escape skips onboarding; “Or type your own answer…” lets you submit a different request. Type /demo to start again. See CI/CD analytics demo. The banner and prompt show CI/CD fixes: distinct GitHub repairs whose pushed checks passed, including merge-conflict repairs. A repair can count before it is merged; check the target branch before assuming it is green. Fixes in this shell update the prompt immediately. Use /clear to pick up fixes saved by another OpenSRE process in the same deployment. Zero also covers an unavailable count; the total is best-effort and can decrease after restarting if a save failed.

Quick reference

Help and exit

Command	What it does
`/help`	List commands or show help for one command or category
`/?`	Shortcut for `/help`
`/exit`	Leave the interactive shell
`/quit`	Alias for `/exit`

Session

Command	What it does
`/status`	Session summary — interactions, alerts, provider, effort, trust mode
`/cost`	Token usage and LLM call count for the current session
`/context`	Infra metadata accumulated during the session
`/effort`	Set or show reasoning effort (`low` … `max`)
`/auto`	Tool-approval autonomy (`off` / `low` / `med` / `high`; default `high`)
`/trust`	Enable or disable trust mode (skip confirmation prompts)
`/verbose`	Toggle verbose logging
`/clear`	Clear the screen and re-render the banner
`/compact`	Summarize older context into a replayable compaction entry
`/sessions`	List recent REPL sessions on disk
`/resume <id>`	Restore a past session’s conversation context
`/resume <id>:<entry>`	Restore a specific session branch point
`/new`	Start a new session file while keeping LLM context
`/goal`	Set a finish line and keep working toward it across turns — see Goals

Integrations, models, and tools

Command	What it does
`/health`	Integration and agent health check
`/verify`	Verify integration connectivity (all or one service)
`/integrations`	List, verify, show, setup, or remove integrations
`/mcp`	List, connect, or disconnect MCP servers
`/model`	Show the account-managed hosted model
`/tools`	List registered chat and action tools

Privacy and history

Command	What it does
`/history`	Show or manage persisted command history
`/privacy`	History persistence, redaction status, and threat model

Tasks and background work

Command	What it does
`/loops`	List, create, run once, and debug recurring prompt loops
`/tasks`	List recent and in-flight background tasks
`/work`	List, add, complete, and prioritize human work items
`/cancel <id>`	Cancel a running task by id elevated
`/stop`	Guidance for stopping background work
`/gateway`	Start, stop, or inspect the background gateway daemon

Agents and alerts

Command	What it does
`/fleet`	View and manage the local AI agent fleet
`/alerts`	Alert listener inbox status
`/choose`	Reopen the selection menu the agent is waiting on

CLI parity

These commands delegate to the same Click CLI you would run outside the REPL.

Command	What it does
`/account`	Sign in to OpenSRE, inspect the local account, or sign out
`/auth`	Log in to LLM providers, show provider auth status, or clear credentials
`/login`	Shortcut for `/auth login` (`/login openai`, `/login anthropic`, `/login deepseek`)
`/onboard`	Interactive onboarding wizard
`/remote`	Connect to and operate remote deployed agents
`/remote-sync`	Manage remote sync to your object store. Subcommands: `status`, `sync`, `setup`. See Sync to your own object store.
`/config`	Show or edit `~/.opensre/config.yml`
`/cron`	Manage scheduled delivery jobs
`/sentry`	Schedule automated Sentry morning digests or uptime watches (Telegram or Slack required)
`/messaging`	Telegram pairing and allowlist
`/guardrails`	Sensitive-information guardrail rules
`/update`	Check for updates and upgrade OpenSRE
`/posthog`	Run or schedule PostHog per-metric summary reports
`/runbooks`	Manage trusted runbook sources for guided investigations
`/debug`	Targeted runtime diagnostics
`/uninstall`	Remove OpenSRE and local data elevated

System

Command	What it does
`/doctor`	Full local environment diagnostic
`/version`	OpenSRE, Python, and OS versions
`/theme`	Choose and persist the shell colour theme

Commands with interactive menus (TTY)

Bare invocation opens a picker or submenu:

Command	Menu behavior
`/help`	Browse categories; Enter runs the selected command
`/integrations`	list / verify / show / setup / remove
`/mcp`	list / connect / disconnect
`/model`	show / set / restore / toolcall
`/theme`	Pick a colour theme from the installed list
`/choose`	Reopen the selection menu the agent queued
`/trust`, `/verbose`	on / off
`/history`	show / clear / off / on / retention
`/resume`	Numbered list of recent sessions

/model keeps its menu running: picking show prints the current models and hands you back to the menu, so leave it with done or Esc.

Commands

Help

/help

/help
/help /model
/help tasks
/help all

Form	Result
`/help`	Interactive picker in a TTY; category index otherwise
`/help <command>`	Detailed usage for one command (e.g. `/help /model`)
`/help <category>`	All commands in a section (`session`, `tasks`, …)
`/help all`	Full command index

Help categories mirror the REPL grouping: Quick Access, Session, Integrations/Models/Tools, Privacy, Tasks, Agents, Alerts, CLI parity, and System.Quick Access duplicates frequently used commands (/integrations, /model, /health, /status, /help) for faster discovery in the picker.

Shortcut for /help. Same forms and picker behavior.

Session

/status

Shows a snapshot of the current REPL session:

/status

Typical fields:

Field	Meaning
`interactions`	Count of recorded turns (chat, slash, alerts)
`incoming alerts`	Alerts received by the local listener this session, plus age of the latest
`trust mode`	`on` / `off`
`reasoning effort`	Current `/effort` level (OpenAI/Codex only)
`provider`	Active `LLM_PROVIDER`
`grounding … cache`	Doc/source cache stats used for help answers
`accumulated context`	Comma-separated keys from prior turns (e.g. `service`, `cluster`)

Use /status for session state. Use /health for integration connectivity.

/cost

Shows LLM usage tracked locally for the current REPL session. This is not cloud-provider billing and does not read your vendor invoice.

/cost

Example output (measured + estimated mix):

  Session cost (includes estimates)

  history entries     12
  llm calls           8
  input tokens        4,210 (measured: 1,200 · estimated: 3,010)
  output tokens       890 (estimated: 890)

Field	Meaning
`history entries`	Lines recorded in this session’s in-memory history
`llm calls`	LLM turns counted (planner + chat + help + follow-up)
`input tokens` / `output tokens`	Running totals for prompt and completion usage

Measured vs estimated:

Code path	Token source
Planner `invoke()` (action selection)	Provider usage metadata when the API returns it
Streaming chat, help, follow-up	Estimated from character length (~4 characters per token)

When any estimate is included, the table title notes (includes estimates) and rows show measured vs estimated splits.What increments the counter: Normal LLM chat turns and planner calls. What does not: Non-LLM command handling such as history recall or prompt rendering.Token totals reset on /new or when session identity is rotated. They do not carry across /resume. See Session History.

/context

Displays key/value infra metadata collected during chat — typically service, cluster, region, or similar fields extracted from alert text and tool results.

/context

Context is inherited across turns in the same session (and restored by /resume), so the agent does not re-ask for environment details you already established.

/effort

Set reasoning depth for OpenAI and Codex providers in this REPL session only.

/effort high
/effort

Level	When to use
`low`	Fast triage, simple lookups, lower token cost
`medium`	Default balance for most incident work
`high`	Deeper analysis when latency is acceptable
`xhigh`, `max`	Maximum reasoning; best with newer GPT-5 or Codex models — older models may reject these levels

Bare /effort prints the current level, the config default for your provider/model, and supported choices. /status includes the same field.Other providers (Anthropic, Ollama, etc.) ignore /effort; the shell prints a hint suggesting /model set openai or /model set codex. Set OPENSRE_REASONING_EFFORT in the environment for non-interactive defaults. See LLM providers.

/auto

Set how often the REPL asks before running agent tools. Shown on the status line as Auto (Med) · ….

/auto
/auto med
/auto high

Level	Prompts before
`high` (default)	Nothing — alpha default; every tool runs immediately
`med`	Mutating agent tools: shell, code agent, slash/CLI, synthetic tests, LLM provider switch, Sentry issue fix, …
`low`	Everything `med` asks about, plus additional tool starts
`off`	Every tool type

/auto is not a shell-command allowlist: under alpha, shell strings still run when approved (or when High skips the prompt). Lower levels only promote the existing ask confirmation hook by tool_type.With /trust: /trust on skips approval prompts even when /auto would ask. Turn trust off to restore /auto prompts.Session preference only — not restored by /resume. Bare /auto prints the current level, the default, and each caption.

/trust

Trust mode skips execution confirmation prompts for elevated commands (/cancel, /uninstall, integration remove, etc.).

/trust on
/trust off
/trust

In a TTY, bare /trust opens an interactive on/off menu. Trust mode is a session preference — it is not restored by /resume.

/verbose

Toggle TRACER_VERBOSE logging for the REPL process (deeper internal logs to stderr). Also shows the per-turn tool-call log above each reply; by default it is hidden and only reachable with Ctrl+O.

/verbose on
/verbose off
/verbose

/clear

Clears the terminal and re-renders the OpenSRE banner. Does not reset session state, token usage, LLM conversation context, or accumulated infra context.

/clear

/compact

Summarizes older conversation context, keeps recent messages, and persists a compaction entry in the session file. Future /resume calls replay the summary before the kept messages.

/compact

If there are not enough messages to compact, the command reports nothing to compact. OpenSRE also compacts automatically before a shell turn when the replayed branch context exceeds the runtime threshold.

/sessions

List up to 20 recent sessions stored on disk, newest first:

/sessions

  Recent sessions

   #  Session ID  Name                           Started            Duration  Turns
   ───────────────────────────────────────────────────────────────────────────────
   1  3f8a1c2d    (current)                      Jun 17 10:00       42m       8
   2  9b2e4f7a    why is CPU spiking on prod-api Jun 16 14:30       1h 5m    15

Column	Meaning
`Session ID`	First 8 characters of the UUID (enough for `/resume`)
`Name`	Derived from the first user message or resumed session label
`Turns`	Total chat + slash + alert turns recorded

The current row updates duration live. Sessions with no name show (current) or ↩ <resumed-from> when applicable.

/resume

Restore LLM conversation context and accumulated infra context from a previous session.

/resume 9b2e4f7a
/resume 9b2e4f7a:abc123
/resume redis
/resume

Form	Behavior
ID prefix	Match session UUID by prefix (must be unique)
ID + entry prefix	Replay the branch ending at the matching entry ID prefix
Name substring	Match when ≥3 characters and exactly one session matches (e.g. `/resume redis`)
Bare `/resume`	Interactive numbered picker of recent sessions (TTY)

Current session: If the ID prefix matches the session you are already in, /resume is a no-op — OpenSRE prints a hint to pick a previous session from /sessions.When you resume a different session, OpenSRE:

Switches the active session file to the target session
Restores cli_agent_messages so the assistant remembers prior turns
Restores accumulated_context keys
Reprints conversation history (user prompts, assistant replies, slash commands)

Compaction entries are replayed as summary messages before the kept branch messages.Restored vs not restored:

	`/resume`
Conversation context	Yes
Infra context keys	Yes
Trust mode, reasoning effort	No — per-session preferences
Token usage / `/cost` counters	No — fresh counters for the resumed session identity
In-memory history count	Yes — turn stubs from the saved session

Warning: Resuming a different session replaces the current session’s LLM context if messages already exist.Session replay reads the current version-2 session tree format. Older session files are ignored by /sessions and /resume. See Session History.

/new

Rotate to a new session file while keeping the current LLM conversation thread and accumulated context.

/new

new session started — conversation context carried forward.
  14 messages in context · type to continue

Command	Session file	LLM context	Token counters
`/clear`	Same	Kept	Kept
`/new`	New UUID	Kept	Reset
`/resume`	Target session	Replaced with target	Reset for that session

Use /new after a long /resume so /sessions stays tidy without losing your place in the conversation.

/goal

Set a finish line and keep working toward it across turns:

/goal
/goal set How many Windows users signed up last week?
/goal set --max-turns 4 Prefer live PostHog if connected
/goal pause
/goal resume
/goal edit <updated condition>
/goal clear

Bare /goal shows the current goal. /goal set starts work immediately. See Goals for the full workflow.

Integrations, models, and tools

Choosing the right diagnostic command

Question	Command
Are my integrations configured and reachable?	`/verify`, `/health`, or `/integrations verify`
Verify one integration by name?	`/verify datadog` or `/integrations verify datadog`
Show one integration’s credentials/endpoints?	`/integrations show datadog`
Is Python/Docker/venv OK on this machine?	`/doctor`
What integrations exist in OpenSRE generally?	Ask in plain language (docs answer) — not `/integrations list`

/health

Read-only pass/fail report for the local OpenSRE agent, LLM connectivity, and each configured integration.

/health

Runs live verification against the integration store. Use before incidents to confirm Datadog/Grafana/K8s credentials still work. For integration-only checks without the full agent/LLM report, prefer /verify.

/verify

Shortcut for integration connectivity checks (same as opensre integrations verify / make verify-integrations).

/verify
/verify datadog
/verify telegram

Form	Behavior
Bare `/verify`	Verify all integrations; prints status table plus `all integrations ok` or `N integration(s) need attention`
`/verify <service>`	Verify one named integration

/integrations

/integrations
/integrations list
/integrations verify
/integrations verify datadog
/integrations show datadog
/integrations setup datadog
/integrations remove datadog

Subcommand	Behavior
`list` (default)	Verify all configured integrations and render status table
`verify`	Verify all integrations; prints summary line
`verify <service>`	Verify one integration (same as `/verify <service>`)
`show <service>`	Verify one service and print key/value config (masked secrets)
`setup <service>`	Launch setup wizard via CLI subprocess
`remove <service>`	Remove from local store elevated

Bare /integrations opens an interactive menu in a TTY with service pickers for show/remove.

/mcp

MCP-capable integrations only (subset of the full integration catalog).

/mcp list
/mcp connect github
/mcp disconnect github

Subcommand	Maps to
`list`	Table of MCP servers from verified integrations
`connect <server>`	`opensre integrations setup <server>`
`disconnect <server>`	`opensre integrations remove <server>`

/model

Show the active hosted model. An authenticated interactive shell is account-managed, so local provider/model changes are locked until sign-out; signing out closes the shell.

/model show
/model set openai gpt-4.1
/model set anthropic claude-sonnet-4-20250514 --toolcall-model claude-sonnet-4-20250514
/model set claude-sonnet-4-20250514
/model restore
/model restore anthropic
/model toolcall set gpt-4.1-mini
/model

Subcommand	Behavior
`show` (default)	Show provider and reasoning/toolcall model slots
`set <provider> [model] [--toolcall-model <m>]`	Refuse the local change while the account route is active
`set <model>` (no provider)	Refuse the local change while the account route is active
`restore [provider]`	Refuse the local change while the account route is active
`toolcall set <model>`	Refuse the local change while the account route is active

Account lock: set, restore, and toolcall set explain that the model is managed by the OpenSRE account and make no change. The account route overrides local provider variables for every model role while the session is signed in.Bare /model: in a terminal this opens a menu rather than printing the table. The menu stays open: show prints the current models and hands you back to it, so leave with done or Esc. set, restore and toolcall close it once the change succeeds. Use /model show when you only want the table.Reasoning vs toolcall model: Reasoning model drives chat and planning; toolcall model drives tool invocation when the provider exposes a separate slot (common on Anthropic/OpenAI).See LLM providers.

/tools

List tools available to the chat and action surfaces in this build (name, source, surfaces).

/tools
/tools list

There is no global /list command — use domain-specific list commands (see Natural language actions).

Privacy and history

Command history (up-arrow recall) is separate from session history (/sessions). Full redaction patterns and env vars: Interactive Shell Privacy.

/history

/history
/history clear
/history off
/history on
/history retention 1000

Subcommand	Behavior
(none)	Numbered list of persisted prompt lines
`clear`	Delete `~/.opensre/interactive_history`; up-arrow recall empty on next launch
`off`	Pause disk writes for this session (in-memory recall still works)
`on`	Resume persistence
`retention <N>`	Cap file entries; prunes immediately (requires redacting backend)

Bare /history opens an interactive menu in a TTY (presets: 100, 500, 1000, 5000 for retention).

Redaction applies to the history file, not necessarily to what is sent to the LLM. Treat shared machines accordingly — run /history clear after sensitive sessions.

/privacy

/privacy

Shows persistence on/off, redaction on/off, retention cap, history file path, built-in pattern count, and a short threat-model reminder (unencrypted local disk).

Tasks and background

Long-running work is tracked in a per-session task registry surfaced by /tasks. Human todos and reminders are tracked separately by /work.

Task kinds

Kind	Source
`cli_command`	Delegated CLI subprocesses
`code_agent`	Code-agent integrations (when used)

Task statuses

Status	Meaning
`running`	In progress; `/cancel` eligible
`completed`	Finished successfully
`cancelled`	User or `/cancel` stopped it
`failed`	Non-zero exit or pipeline error
`pending`	Created but not yet started

/gateway

Control the background OpenSRE gateway daemon, which runs the web health app, Telegram chat, and the task scheduler. Scheduled work needs a scheduler running: this daemon, or opensre cron start in the foreground.

/gateway
/gateway start
/gateway stop
/gateway status
/gateway logs
/gateway logs 100

Subcommand	Behavior
`status` (default)	Running state and pid, plus a line per component
`start`	Start the daemon in the background
`stop`	Stop the running daemon
`logs [lines]`	Tail the log, 30 lines by default

Logs are written to ~/.opensre/gateway/gateway.log. Same daemon as opensre gateway.

/tasks

/tasks

Example:

  Tasks

  id      kind           status     started (UTC)     duration  detail
  def34   cli_command    completed  2026-06-17 09:55  120.0s    opensre health

Shows up to 50 recent tasks, newest first. Use the id column (short prefix) with /cancel.

/work

/work
/work add &lt;title&gt;
/work done &lt;id-or-title&gt;
/work next
/work path

Human todos, reminders, and follow-ups — separate from /tasks (runtime jobs). See Work Management.You can also ask naturally:

Add task "finish Slack reminder smoke test" for the hackathon, priority high.
What should I focus on next?

/cancel

/cancel abc12

Matches task id by prefix (must be unique among active/recent tasks)
Only running tasks accept cancellation

/stop

Prints guidance only — does not kill processes:

/stop

Situation	Action
Streaming turn	Ctrl+C
Background CLI task	`/tasks` → `/cancel <id>`

Agents and alerts

Fleet coordination is documented further on Agents. Register discovered agents with opensre fleet scan --register before /fleet trace targets them.

/fleet

/fleet
/fleet budget
/fleet budget cursor-agent 5.00
/fleet bus
/fleet claim feature-x my-agent
/fleet release feature-x
/fleet conflicts
/fleet kill 12345
/fleet kill 12345 --force
/fleet trace 12345
/fleet wait 12345 --on 67890
/fleet graph

Subcommand	Behavior
(none)	Dashboard: registered + discovered agents (Cursor, Claude Code, Codex, Aider, …) with pid, uptime, CPU, tokens/min, $/hr, status
`budget`	View hourly budgets from `~/.opensre/agents.yaml`
`budget <agent> <usd>`	Set `hourly_budget_usd` for one agent
`bus`	Live-tail cross-agent context bus until Ctrl+C
`claim <branch> <agent>`	Exclusive branch claim (agent must be in registry)
`release <branch>`	Release a claim
`conflicts`	File-write conflict report between agents
`kill <pid> [--force]`	SIGTERM → wait → SIGKILL elevated; refuses self-PID
`trace <pid>`	Live stdout tail of agent process
`wait <pid> --on <other-pid>`	Record wait dependency for graph
`graph`	Tree of wait-on relationships

Kill confirmation: Without --force, prompts [y/N]. --force skips prompt (still elevated tier unless trust mode).

/choose

Reopen the selection menu the agent is waiting on. Useful when the menu scrolled away, or you dismissed it with Esc and want it back.

/choose

Prints No selection menu is pending. when the agent has not asked anything. Outside a TTY it lists the options as text for you to answer in a reply instead of opening a picker — except for a pending onboarding demo choice, which it drops with “Guided demo selection is unavailable here”, leaving you to ask for what you want directly.

/alerts

/alerts

When the alert listener is active:

Field	Meaning
`status`	`listening`
`queue depth`	Alerts waiting for REPL consumption
`dropped`	Alerts dropped when queue was full
`recent`	Up to 5 latest alert names/snippets

If the listener is inactive, prints a warning. Incoming alerts also appear in /status as incoming alerts. Post alerts to your configured webhook/listener URL during setup; the REPL triages them in chat.

Setup and ops (CLI parity)

These spawn opensre … subprocesses. Output is captured into the REPL buffer for non-interactive subcommands; wizards attach to the real TTY.

/account

/account
/account login
/account status
/account usage
/account logout

Sign in to a personal OpenSRE account, inspect the local login, open the credits and top-up page (/account usage, opens your browser; from a chat it replies with the link), or sign out. Same as opensre account. The browser opens the OpenSRE sign-up page, where you can use email or any enabled sign-in provider. The shell starts only for an active account state. /account logout revokes the saved session, invalidates the hosted-model route, and closes the shell before another turn. If OPENSRE_ACCOUNT_TOKEN is set in the environment, it overrides the token saved by login until you unset it.

/setup

/setup
/setup --dev

Run the first-use webapp account flow. It creates or signs in to an OpenSRE account using email or another enabled provider and activates the account-hosted model. Use --dev for a webapp running at http://localhost:3000. Setup requires exclusive stdin because browser authorization prompts on the real TTY.

/auth

/auth
/auth status
/auth login deepseek
/auth logout deepseek
/auth verify anthropic

Log in to LLM providers, show local auth status, or clear stored credentials. Same as opensre auth. Interactive login prompts on the real TTY.

/onboard

/onboard
/onboard local_llm

Optional local LLM-provider onboarding. The account-hosted route remains authoritative while signed in, so this does not switch the model used by the interactive shell.

/remote

/remote health
/remote ops
/remote pull
/remote trigger

Operate remote deployed OpenSRE agents (EC2, Nitro, hosted runtime).

/remote-sync

/remote-sync
/remote-sync status
/remote-sync sync
/remote-sync sync --dry-run
/remote-sync setup --provider aws --bucket my-opensre-bucket

Copy sessions and memory to an object store you own (S3, GCS, Azure, Vercel Blob, or S3-compatible). Credentials and API keys stay local. See Sync to your own object store.

/config

/config show
/config set interactive.history.max_entries 1000

Read/write ~/.opensre/config.yml. Prefer env vars for secrets; use config for structured interactive-shell settings.

/cron

/cron list
/cron add
/cron remove &lt;id&gt;
/cron run &lt;id&gt;
/cron logs &lt;id&gt;

Scheduled report delivery. See Cron.

/loops

/loops
/loops active
/loops all
/loops show
/loops show &lt;name-or-id&gt;
/loops show &lt;name-or-id&gt; --run &lt;run-id&gt;
/loops add --name "Morning ops" --time 08:30 --prompt "Check open incidents and summarize production risk" --run-now
/loops add --name "CI fix agent" --cron "*/30 * * * * *" --mode agent --prompt "Repair failing PR checks with fix_github_pr_ci"
/loops run &lt;loop_id&gt;
/loops stop &lt;loop_id&gt;
/loops start &lt;loop_id&gt;
/loops delete &lt;loop_id&gt;
/loops next &lt;loop_id&gt;
/loops messages

List recurring loops from the scheduler store, create manual prompt loops, run a loop once immediately, stop or restart a loop, delete a loop, and debug the next fire time. By default a loop tick only produces a report; add --mode agent when the tick should act with tools (for example edit and push CI fixes). Onboarding creates draft examples such as a weekday morning report; active loops run through the cron scheduler when the gateway or opensre cron start is running.Agent-mode prompts must contain the complete task and name the tools to use; each tick starts a fresh session without loading workflow skills. For the CLI equivalent, use opensre cron add --kind manual_loop --mode agent with your prompt and schedule. Existing loops retain their stored mode; check /loops show <id> before reusing one.The list shows each loop’s latest finding and run status, plus its next scheduled time in your local timezone. Failed and quiet runs replace the previous result in the table.Use /loops show to pick a loop, or pass its name or ID directly. Details contain the full report, recent runs, and configuration. Open an earlier report with the run ID shown in its history. New reports are retained even when delivery fails; older reports may be unavailable.You can also ask naturally:

Set up a manual loop called Morning ops at 08:30 UTC to check open incidents and summarize production risk, and run it once now.

By default, new loops send to every configured default handle OpenSRE can reach: Telegram, Slack, and the local interactive-shell inbox.

/sentry

/sentry digest run
/sentry digest schedule list
/sentry digest schedule add --cron "0 8 * * *" --provider telegram --chat-id &lt;id&gt;
/sentry digest schedule run &lt;id&gt;
/sentry digest schedule remove &lt;id&gt;
/sentry uptime check
/sentry uptime watch list
/sentry uptime watch add --cron "*/5 * * * *" --provider telegram --chat-id &lt;id&gt;
/sentry uptime watch run &lt;id&gt;
/sentry uptime watch remove &lt;id&gt;

Automated Sentry morning digest delivery (#10) and uptime watch notifications (#4032). Requires Sentry plus Telegram or Slack configured for the chosen provider. See Sentry.

/messaging

/messaging pair
/messaging allow
/messaging revoke
/messaging status

Telegram bot pairing and sender allowlist for two-way chat and delivery features.

/guardrails

/guardrails audit
/guardrails init
/guardrails rules
/guardrails test

Subcommand	Purpose
`init`	Scaffold local guardrail config
`rules`	List active masking rules
`test`	Run sample text through rules
`audit`	Scan recent content for sensitive patterns

Related: Masking.

/update

/update

Checks PyPI and upgrades OpenSRE in-place (5-minute network timeout). Non-zero exit prints CLI error code.

/posthog

Run or schedule automated PostHog per-metric summary reports. Requires the PostHog integration; see PostHog.

/posthog report run
/posthog report schedule list
/posthog report schedule add
/posthog report schedule run <id>
/posthog report schedule remove <id>

A scheduled report only fires while a scheduler is running, so pair it with /gateway start or opensre cron start. Same as opensre posthog.

/runbooks

Manage the trusted runbook sources the agent may read during guided investigations. See Runbook-guided investigations.

/runbooks list
/runbooks add github --name <name> --repo <owner/repo>
/runbooks verify <name>
/runbooks remove <name>

The agent reads runbooks only from sources listed here; an untrusted repository, an unsafe path, or a non-Markdown document is rejected. Same as opensre runbooks.

/debug

/debug sentry

Targeted smoke tests (Sentry, etc.) — subcommands match opensre debug --help.

/uninstall

/uninstall

Removes OpenSRE and local data. Destructive — confirmation required unless trust mode. Delegates to interactive CLI uninstall flow.

System

/doctor

Environment diagnostic distinct from /health:

/doctor

Checks Python version, venv, config paths, Docker availability, credential presence, and related local prerequisites. Each row: ok, warn, or error with detail text.Use /doctor before first install debugging; use /health before an incident to verify integrations.

/theme

Choose the shell colour theme. The choice persists to interactive.theme in ~/.opensre/config.yml, so it survives restarts.

/theme
/theme nord

Bare /theme opens a picker with the current theme preselected, and needs a TTY. Passing a name sets it directly and reports an unknown name with the full list.Installed themes: green, blue, amber, mono, red, pink, purple, orange, teal, lime, nord, dracula, solarized, gruvbox, webflux, sunset. The default is purple.

/version

/version

Field	Example
`opensre`	Package version from install
`python`	`3.12.x`
`os`	`darwin (arm64)`

/exit and /quit

/exit
/quit

Clean shutdown with a /resume hint. Prefer this over killing the terminal so session files flush cleanly./exit, /quit, double Ctrl+C, or Ctrl+D (empty prompt) all print something like:

Resume this session with:
/resume 3f8a1c2d
opensre --resume 3f8a1c2d
goodbye.

Trust mode, `/auto`, and confirmations

Two controls decide whether the REPL prompts before an action:

Control	Role
`/auto`	Which agent tool types need approval (default high = none)
`/trust`	Session override that skips approval prompts when `/auto` (or an elevated slash command) would ask

Tier	Examples	Confirmation
Exempt	`/help`, `/exit`, `/trust`, `/auto`	Never prompts
Safe	`/status`, `/health`, `/integrations list`	Read-only or standard risk
Elevated	`/cancel`, `/integrations remove`, `/fleet kill`, `/uninstall`	Prompt unless trust on

Non-TTY: actions that would ask fail closed (error message, no side effect).

/auto med   # ask before mutating agent tools
/auto high  # alpha default — no tool prompts
/trust on   # skip prompts for this session
/trust off  # restore /auto (and elevated) prompts

Natural language actions

You do not need to memorize every slash command. Examples:

You type	Typical action
”what’s my token usage?”	`/cost`
”verify datadog”	`/verify datadog`
”show datadog config”	`/integrations show datadog`
”show the active model”	`/model show`
”list my past sessions”	`/sessions`
”check health then list integrations”	`/health` then `/integrations list`
”how do I configure Datadog?”	Doc-grounded answer (no mutating command)

List intents — there is no global /list:

Intent	Command
Connected integrations	`/integrations list`
Tools	`/tools`
Background tasks	`/tasks`
Human todos and reminders	`/work`
MCP servers	`/mcp list`
Cron jobs	`/loops` or `/cron list`
Past REPL sessions	`/sessions`

When the planner is uncertain, it asks for clarification or falls back to help — it does not silently run elevated commands. Compound requests (“health then integrations”) execute as an ordered sequence of slash actions.

Common workflows

First-time setup

/account status
/health
/verify
/model show

opensre setup must establish the account before this workflow is reachable. Every launch opens the demo picker — Escape continues to the prompt. The recommended option analyzes CI/CD performance; see CI/CD analytics demo.

Incident triage (local)

/status
/alerts
/health

Paste alert text or describe the incident in plain language and the agent will triage it with your connected integrations.

Pick up yesterday’s thread

/sessions
/resume 9b2e4f7a

Continue chatting, then optionally:

/new

Inspect account and model state

/account status
/model show
/cost

Debug integration failures

/integrations show datadog
/doctor
/verbose on

Troubleshooting

Symptom	Try
`unknown command`	`/help`; check spelling; use suggested correction
Elevated command blocked in CI	Use the CLI equivalent or run interactively
`/cost` shows zero	No LLM turns yet this session; chat once and retry
`/resume` not found	Run `/sessions`; use longer ID prefix
`/resume` ambiguous prefix	Add more characters from Session ID column
`/model set` reports an account lock	The hosted model is working as designed; `/account logout` closes the shell rather than switching it to a local provider
`/integrations show` not found	Run `/integrations list` for exact service slug
History pause not working	Requires redacting backend — see `/privacy`
Garbage in next prompt after table	Known TTY issue — upgrade OpenSRE; report if persistent

Goals — /goal set, pause, resume, edit, clear
Session History — persistence format, privacy, /new vs /clear
Interactive Shell Privacy — redaction, env vars, threat model
LLM providers — /model and /effort
Agents — fleet dashboard, bus, trace, budgets
Cron — /cron scheduled deliveries
Sync to your own object store — /remote-sync

Scheduled CI repair demo

Choose scheduled CI repair from /demo to try a tiny failure in the private opensre-onboarding-ci-repair-demo repository. OpenSRE creates that repository once and reuses it, with a fresh branch and PR for each completed demonstration. An existing unrelated repository with that name stops setup. The demo starts on the next scheduled minute and has a ten-minute total limit. It uses the macOS or Linux background scheduler so it can finish after you close the terminal. Configure GitHub and authenticate your coding agent before starting. The initial run also needs permission to create a private repository and workflow.

Read the complete outcome and evidence links with /loops show <task-id>.
Stop an active repair with /loops stop <task-id>.
Starting the demo again while it is active returns the same run and deadline.
Successful runs close the demo PR and remove its branch. Unsuccessful runs keep the PR, branch, and diagnostics. The repository and stopped loop history remain.

Overview

First steps

How the REPL works

Quick reference

Help and exit

Session

Integrations, models, and tools

Privacy and history

Tasks and background work

Agents and alerts

CLI parity

System

Commands with interactive menus (TTY)

Commands

Help

Session

Integrations, models, and tools

Privacy and history

Tasks and background

Agents and alerts

Setup and ops (CLI parity)

System

Trust mode, `/auto`, and confirmations

Natural language actions

Common workflows

First-time setup

Incident triage (local)

Pick up yesterday’s thread

Inspect account and model state

Debug integration failures

Troubleshooting

Scheduled CI repair demo

​How the REPL works

​Quick reference

​Help and exit

​Session

​Integrations, models, and tools

​Privacy and history

​Tasks and background work

​Agents and alerts

​CLI parity

​System

​Commands with interactive menus (TTY)

​Commands

​Help

​Session

​Integrations, models, and tools

​Privacy and history

​Tasks and background

​Agents and alerts

​Setup and ops (CLI parity)

​System

​Trust mode, /auto, and confirmations

​Natural language actions

​Common workflows

​First-time setup

​Incident triage (local)

​Pick up yesterday’s thread

​Inspect account and model state

​Debug integration failures

​Troubleshooting

​Related docs

​Scheduled CI repair demo

How the REPL works

Quick reference

Help and exit

Session

Integrations, models, and tools

Privacy and history

Tasks and background work

Agents and alerts

CLI parity

System

Commands with interactive menus (TTY)

Commands

Help

Session

Integrations, models, and tools

Privacy and history

Tasks and background

Agents and alerts

Setup and ops (CLI parity)

System

Trust mode, `/auto`, and confirmations

Natural language actions

Common workflows

First-time setup

Incident triage (local)

Pick up yesterday’s thread

Inspect account and model state

Debug integration failures

Troubleshooting

Related docs

Scheduled CI repair demo