models
/models
Show which model every agent role runs on, where the value comes from (the config or the default), its rank and whether any reviewer ranks below the role it reviews - one table. Read-only. Use when asked which models the roles use, what the defaults are, or whether the reviewer pairings hold.
- Author
- CodaColaLight ↗
- Repository
- nightmill ↗
- Licence
- Apache-2.0
- Last repository change
- 13.11.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Show which model every agent role runs on, where the value comes from (the config or the default), its rank and whether any reviewer ranks below the role it reviews - one table. Read-only. Use when asked which models the roles use, what the defaults are, or whether the reviewer pairings hold.
Original author description
Show which model every agent role runs on, where the value comes from (the config or the default), its rank and whether any reviewer ranks below the role it reviews - one table. Read-only. Use when asked which models the roles use, what the defaults are, or whether the reviewer pairings hold.
How it works
SKILL.md has no level-two headings · 21 lines, 204 words
SKILL.md preview
---
name: models
description: Show which model every agent role runs on, where the value comes from (the config or the default), its rank and whether any reviewer ranks below the role it reviews - one table. Read-only. Use when asked which models the roles use, what the defaults are, or whether the reviewer pairings hold.
---
Show which model every agent role runs on. This skill reads and changes nothing.
Run the script of the shell in use, from inside the project (any checkout or worktree), and wait for it:
- PowerShell (Windows): `powershell -NoProfile -ExecutionPolicy Bypass -File "${CLAUDE_PLUGIN_ROOT}/scripts/models.ps1"`
- bash: `bash "${CLAUDE_PLUGIN_ROOT}/scripts/models.sh"`
If it exits with 2, show its message and stop: it is a missing or unreadable config, a config that is not a JSON
object, or a call outside a git checkout of the project.
Show the table and the lines below it as the script printed them, then add at most two lines:
1. What is flagged and who fixes it: a `BELOW` row means the owner sets that role's model, or `models.ranking`, in
the config; a `NOT RANKED` row means the model is missing from `models.ranking`; an invalid ranking is fixed in
the config too. The validator (`validate-config`, also run by `/nightmill:init`) reports the same.
2. That nothing was changed.
Do not edit the config or change a model yourself: say what would fix it and let the owner decide. If a line says
that these are the defaults of the schema, say so: the roles run on those models until the config sets them.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · CodaColaLight/nightmill | 82 | Apache-2.0 |
| thomaslangbroek/frugal | 100 | MIT |
| Reevias/Prometheus- | 90 | MIT |
| guaardvark/guaardvark | 90 | MIT |
| imgly/codesign | 90 | MIT |
Database snapshot: 13.11.2026 · package version ecac568464a3 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100codex-agent-creator
Create, validate, install, fold, or troubleshoot Codex subagent role TOML, agents-table config, discoverability wiring, and duplicate-role merges. Use when a user asks for a Codex agent role, reviewer agent, role config, TOML role file, subagent setup, or overlapping agents to merge. - 100may-config
Use when the user wants MAY roles to run on specific models, asks which model each MAY worker uses, or wants to change per-role model settings for Claude Code, Oh My Pi, Codex, or Pi with the pi-subagents extension. - 84route
Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and overlay config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value; fan-out… - 100omp-roles
Use this skill whenever you need the allowed_tools / skills preset for a sub-agent role before calling spawn_subagent. Trigger especially when user mentions: \"role\", \"spawn_subagent\", \"allowed_tools\", or any OMP role name (executor, architect, analyst, critic,… - 90fleet-roles
The role catalogue and the descending-model rule for a multi-session fleet - which roles exist at each tier, what each owns, which model tier each runs on, and when a role should be its own session versus a subagent. Use when standing up a fleet, deciding who owns an activity,… - 100agent-models
Show, check, and change the model and effort every agent role runs on (interactive sessions, /vet reviewers, review panels, audits, Claude subagents and Workflow agents, prun workers) through the one registry at user/agent-models.json. Use when the user asks which model…