Update Models
Skill0 starsChanged 8 days agoNo licenceView on GitHub
TRIGGER when the actual OpenCode model list is stale or a model is missing (e.g. a newly released free model never shows up), when asking for the models refresh/reload command, when distinguishing paid opencode-go/* vs free opencode/* model IDs — including which twin to pick when a model exists under both namespaces — or whenever a model ID is about to be written into opencode.jsonc (check twin + capability gate first); AND when the user wants to review or update their configured models ("which models should I update", "model recommendations", "check my models against the price trackers", "set all models to X", "alle Modelle auf X stellen") — the vision gate and the namespace rule apply to the user''s pick too. Cross-references the configured models with the live ocgo/cc price trackers (prices + changelog), recommends UPDATE vs KEEP, and fixes the namespace from `model-preferences.md`, never from the slug. Also when a model''s context window is far larger than the work needs and the models the config actually uses should carry a capped alias (main agents the larger cap, subagents the smaller one).
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- Agent ConfigSkill
- Build Verify FlowSkill
- CodeGraph Project SetupSkill
- Docker Test ImageSkill
- Generated DocsSkill
- GHCR VisibilitySkill
- GitHub CI FiltersSkill
- LaravelSkill
- Node Dependency PolicySkill
- PermissionsSkill
- Playwright ParallelSkill
- Project GatesSkill
- Ratchet GatesSkill
- React i18nSkill
- Security ReviewSkill
- Skills MarkerSkill
- Tailscale ServeSkill
- UI ReviewSkill
- Web AuditSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

