At a glance
What it does
Configure Ouroboros runtimes, stage models, and LLM backends through a settings UI or chat.
Before you choose it
This skill guides an agent to open the Ouroboros settings interface when a browser is reachable, or to inspect and update the same settings conversationally when it is not. It covers the default agent, per-stage runtimes and models, the internal LLM backend, dependency hints, and confirming changes.
Best for
Ouroboros users who need to change agent, model, runtime, or backend settings.
Common tasks
- Open the local Ouroboros settings page.
- Choose a different runtime or model for a workflow stage.
- Inspect current configuration and apply validated changes from chat.
- Expose settings on a reachable remote host or use an SSH tunnel.
Permissions and data
The skill interacts with Ouroboros configuration and may start a settings server.
Permissions- May read and update `~/.ouroboros/config.yaml` through `ouroboros config show` and `set`.
- May start a local settings web server; remote mode can bind to `0.0.0.0`.
- Configuration values are displayed and changed through the Ouroboros CLI or settings UI.
- No external service is declared; a browser and optional SSH tunnel may be used to reach the settings UI.
- No credential requirement is declared in the supplied evidence.
Limitations
- Requires the `ouroboros` CLI or the documented `uvx` fallback.
- A running MCP server may need reconnection after backend changes.
- Remote hosting requires the user to control network exposure or use the documented SSH tunnel.
- The supplied evidence does not show an installation or runtime test.
What DSHub checked
- The pinned skill document was captured completely.
- The source commit is pinned by the immutable-source check.
- An MIT license is supplied.
What DSHub did not check
- DSHub did not install or execute the skill.
- Actual settings-server behavior and available configuration values were not independently verified.
Pinned install
Primary action
This standalone skill does not have a DSH Plugin install action. Use its source documentation for the delivery method.
Maintainer source
Skill instructions
name: ouroboros-config description: "Open or drive the Ouroboros settings GUI (browser, TUI, or conversational fallback)"
/ouroboros:ouroboros-config
Settings for ~/.ouroboros/config.yaml: per-stage runtime/model selects,
global runtime + LLM backend, install badges for missing CLIs, and
env-override warnings.
Usage
ooo config
/ouroboros:ouroboros-config
Trigger keywords: "ooo config", "open settings", "configure ouroboros", "change model", "change agent"
Instructions
Pick the branch that matches where you (the agent) are running. The decisive question: can the user open a browser pointed at this machine?
Branch A — local harness (Claude Code / Codex on the user's own machine)
Launch in the background (the command serves until stopped):
if command -v ouroboros >/dev/null 2>&1; then ouroboros config else uvx --python '>=3.12' --from 'ouroboros-ai[tui]' ouroboros config fiThe command detects the non-interactive context itself and serves the settings app over a local web server, auto-opening the user's browser. The
uvxfallback is required for a Marketplace-plugin-only install, where the MCP server exists butouroborosis not onPATH. In a development checkout useuv run ouroboros config.Relay the
http://localhost:<port>line from the output so the user can open it manually if the browser did not pop up.Tell the user: edit → Save → then ask you to stop the server. Remind them a running MCP server may need a reconnect to pick up backend changes. Tell them they can reopen these settings any time with
ooo config; saving a model choice never locks it permanently.
Branch B — remote host the user can reach over the network (SSH box, home server)
The user cannot see a browser opened here, but may be able to reach this host. Serve without auto-open and hand over the URL:
ouroboros config --web --host 0.0.0.0 --no-browser
Relay the printed URL with this host's address substituted, plus the SSH
tunnel fallback the command prints
(ssh -L <port>:localhost:<port> <this-host>).
Branch C — chat gateway, no browser path at all (e.g. hermes driven from Discord)
Do NOT start a server nobody can reach. Drive the same settings conversationally over the scriptable surface:
Show the current state:
ouroboros config showPresent the user a short menu in chat — default agent, per-stage agents, per-stage models — with the current values, and ask what to change.
Apply each choice with the validated setter (same write path as the GUI):
ouroboros config set orchestrator.runtime_backend <agent> ouroboros config set orchestrator.runtime_profile.stages.<interview|execute|evaluate|reflect> <agent> ouroboros config set clarification.default_model <model> # interview & seed ouroboros config set execution.default_model <model> # execute ouroboros config set evaluation.semantic_model <model> # evaluate ouroboros config set resilience.reflect_model <model> # reflect ouroboros config set llm.backend <backend> # internal LLM callsConfirm with
ouroboros config showand summarize what changed.
If a set is rejected, relay the validation error verbatim — it lists the
valid keys/values.
All branches
If the command fails with a missing-dependency hint, relay it verbatim
(pip install 'ouroboros-ai[tui]'). Scriptable edits always remain on
ouroboros config show|set|backend|init|validate.
End your final message with the state breadcrumb footer (RFC #1392), e.g.:
◆ Settings GUI serving at <url> → next: Save in browser, then stop the server
◆ Config updated via chat (<keys>) → next: reconnect MCP if the backend changed
RFC #1392 State Breadcrumb Footer
Your final response MUST end with exactly one breadcrumb footer line:
◆ <current state> → next: <recommended action>
Derive <current state> from live session state via ouroboros_session_status when that MCP projection is available; otherwise derive it from this skill's actual outcome. Never use a linear Step N of M footer because Ouroboros is an evolutionary loop. When the next action is genuinely a choice, list 2-3 honest options in the next: clause. The breadcrumb line must be the last line of the response.
Operate deliberately
Install and manage
Prerequisites and target Profile
Target: Codex Profile, Claude Code Profile
Delivery: Skill Files — https://raw.githubusercontent.com/Q00/ouroboros/03714ba446186423dcb46e25d12bd19c3a2e82f6/skills/config/SKILL.md。
Compatibility and access
Supports Ouroboros configuration in local, remote, or chat setups: Not declared in supplied evidence。
Review compatibility evidence ↗
Risk facts
Can update ~/.ouroboros/config.yaml through validated configuration commands.
Evidence ↗Remote mode can serve the settings app on 0.0.0.0 for network access.
Evidence ↗Evidence and editorial reviewManifest, Bundle patch, distribution and freshness
Immutable evidence
Review status and source activity
Approved for publication after reviewing the source-linked content and immutable release record. AI assisted with the draft; the publication decision was human.
Human reviewed Sep 5, 2026, 5:17 PM UTC。GitHub facts last checked Sep 5, 2026, 4:31 PM UTC。
No material source change has been recorded since this evidence baseline.