rundesk-ai/rundesk-cli / src/skills/managing-rundesk
managing-rundesk
VerifiedUse when managing this agent, any other agent in its Rundesk install, or the install itself. It supplies verified operational workflows and safety rules for agent instructions, gateways, conversations, channels, schedules, providers, skills, backups, configuration, credentials, and the Rundesk lifecycle. Do not use for ordinary project work or for deciding, performing, or reviewing delegation.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.0 KB |
| references/agent-instructions.md | markdown | 12.3 KB |
| references/agents.md | markdown | 5.9 KB |
| references/backups.md | markdown | 2.1 KB |
| references/channels.md | markdown | 6.6 KB |
| references/configuration.md | markdown | 3.6 KB |
| references/conversations.md | markdown | 5.3 KB |
| references/gateways.md | markdown | 3.1 KB |
| references/lifecycle.md | markdown | 3.7 KB |
| references/maintenance.md | markdown | 5.9 KB |
| references/oauth-login.md | markdown | 3.4 KB |
| references/permissions.md | markdown | 3.6 KB |
| references/providers.md | markdown | 2.8 KB |
| references/retrospective.md | markdown | 3.8 KB |
| references/schedules.md | markdown | 6.4 KB |
| references/self-improvement.md | markdown | 10.7 KB |
| references/skills.md | markdown | 6.6 KB |
| references/teams.md | markdown | 3.2 KB |
references/configuration.md
View on GitHub# Configuration and values
Rundesk derives every location from `RUNDESK_HOME`. Install settings live in `data/config.json`;
credential values live in `data/secrets/` and are masked in every command output.
## Inspect the install
| Command | Control |
|---|---|
| `status` | Show version, root, program, data, backups, command link, migrations, and health. |
| `version` | Show the installed version and whether the published state is newer, current, or unknown. |
| `configure` | List every owner-settable setting, effective value, and exact flag. |
Always run these as `"$RUNDESK_COMMAND" ...`. `status` is the first answer to path and install
identity questions. Do not construct a path from defaults or set `RUNDESK_HOME` inside a turn.
## Settings
`configure` accepts any combination of current setting flags and applies them atomically:
| Flag | Value |
|---|---|
| `--backup-enabled <yes|no>` | Enable or disable the safety copy made before update carries outstanding install migrations. |
| `--backup-retention <n>` | Keep this many recognized copies when `backups save` prunes older ones. |
| `--update-enabled <yes|no>` | Record whether automatic updates are intended to be enabled. |
| `--update-time <HH:MM>` | Record the intended local time for an automatic update check. |
| `--turn-records-days <n>` | Keep at least one day of detailed tool records. Messages and turn ledger rows remain. |
Run `configure` first because newer releases may add settings. Invalid multi-setting input changes
nothing; a successful call changes every requested setting together.
Automatic upkeep is per-agent rather than an install setting. Inspect `agents`, then use
`agents configure <agent> --self-improve <true|false>`. The protected
`weekly-self-improve-upkeep` policy cannot be enabled, disabled, run, or removed through `schedules`.
A pre-policy owner schedule already using that name remains ordinary owner work and blocks the
automatic policy until the owner removes it; Rundesk never adopts or overwrites it.
`update_enabled` and `update_time` control a root-specific launchd job immediately. It makes one
local-time attempt per day, outside every gateway process tree. An active provider turn or schedule,
or activity Rundesk cannot inspect safely, creates a durable request without fetching, stopping
gateways, or forcing work down. One detached install-level worker waits until the install is quiet,
then performs the automatic or manual request; it is never attached to an agent turn or delegation.
`status` reports configured intent and measured supervisor placement; a reconciliation failure is
non-zero and is repaired idempotently by repeating the same `configure` command.
## Credential values
| Command | Control |
|---|---|
| `env` or `env list` | List names and masked hints, never complete values. |
| `env check <KEY>` | Exit successfully only when the name has a usable value; distinguish missing, empty, and unreadable. |
| `env set <KEY>` | Read a value without echo from a terminal, or from standard input. The value is never an argument. |
| `env unset <KEY>` | Empty the value while retaining its known name. |
Never request, print, echo, or paste a credential into chat or an argument. Give the owner the `env
set` command to type locally. A changed value is available to newly started processes and the next
agent turn; it cannot alter the environment of the current process.
Backups carry the sealed values and their key, so protect them as credential-bearing data. When an
integration failure leaves a value absent, use `env check`, `channels doctor`, or `skills doctor` to
name what the owner must set.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |