Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
luna - Skill - OpenSmartRoute
Skillv1.0.0
luna
Use Luna to watch, grade, or run bounded worker tasks. Use when the user invokes /luna or wants the Luna utility.
Imported from codejunkie99/codex-self-improving-loop (skills/luna/SKILL.md). Install upstream with npx skills add codejunkie99/codex-self-improving-loop --skill luna. Copyright stays with the author.
For grading a loop run, feed the current prompt.md plus log.md to Luna with
the watcher instructions from the self-improving loop. Luna never rewrites
prompts; it grades and emits GOAL, KEPT, WASTED, FAILED, NEXT.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "codejunkie99-codex-self-improving-loop-luna",
"kind": "skill",
"name": "luna",
"description": "Use Luna to watch, grade, or run bounded worker tasks. Use when the user invokes /luna or wants the Luna utility.",
"publisher": "codejunkie99",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Use Luna to watch, grade, or run bounded worker tasks. Use when the user invokes /luna or wants the Luna utility."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/codejunkie99/codex-self-improving-loop",
"path": "skills/luna/SKILL.md",
"ref": "c3b625d6d3eb650cd2903b2503c2a1825f94d3e6",
"url": "https://github.com/codejunkie99/codex-self-improving-loop/blob/c3b625d6d3eb650cd2903b2503c2a1825f94d3e6/skills/luna/SKILL.md",
"key": "codejunkie99/codex-self-improving-loop/skills/luna/SKILL.md"
}
},
"instructions": "# Luna utility\n\nRun the task on `gpt-5.6-luna` with the Codex CLI:\n\n```bash\ncodex exec -m gpt-5.6-luna -s read-only --skip-git-repo-check --ephemeral -C . \"<task>\"\n```\n\nFor grading a loop run, feed the current `prompt.md` plus `log.md` to Luna with\nthe watcher instructions from the self-improving loop. Luna never rewrites\nprompts; it grades and emits GOAL, KEPT, WASTED, FAILED, NEXT.",
"cost": {
"context_tokens": 96
}
}
Fetch it by URL: GET /api/v1/registry/codejunkie99-codex-self-improving-loop-luna/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
