A command for choosing which AI model each SCV command uses and applying that choice to the commands' settings. The choice is saved in the project's .env file so it can be reused later.

Use it to choose a recommended mix of models, use one model for every command, or balance response quality and cost across SCV work.

It avoids changing model settings one command at a time and keeps the choice when command templates are updated.

set-models — Command for coding agents by wookiya1364: A command for choosing which AI model each SCV…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/wookiya1364/scv-claude-code/set-models

Clone the repo

git clone --depth 1 https://github.com/wookiya1364/scv-claude-code

Or install scv, the plugin that ships this one along with the rest of its 1 skill, 15 commands, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/wookiya1364/scv-claude-code/set-models.svg)](https://agentmods.dev/commands/wookiya1364/scv-claude-code/set-models)

Your own site

<a href="https://agentmods.dev/commands/wookiya1364/scv-claude-code/set-models"><img src="https://agentmods.dev/badge/commands/wookiya1364/scv-claude-code/set-models.svg" alt="Measured on agentmods" height="20"></a>

Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,647 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00088	$0.01647
Opus 5	$0.00044	$0.00823
Sonnet 5	$0.00018	$0.00329
Haiku 4.5	$0.00009	$0.00165

Measured today against content hash f8854f4b0085, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

set-models scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. `~/.claude/settings.json` (or project `.claude/settings.json` / `.claude/settings.local.json`) — `language` key (Claude Code official).

commands/set-models.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/scv:set-models

Apply a model policy to all SCV commands and remember the choice in scv/scv_settings.json. The shipped default is the session model.

Language preference

Resolve the user's preferred language with this priority, then use it for ALL user-facing output (AskUserQuestion text, summaries):

~/.claude/settings.json (or project .claude/settings.json / .claude/settings.local.json) — language key (Claude Code official).
Project .env — SCV_LANG.
Auto-detect from the user's most recent message language.
Default to English.

Technical identifiers stay as-is: policy names (recommended, all-opus, all-sonnet, all-haiku, session-default), env var names (SCV_MODEL_POLICY, SCV_LANG), file paths, model names (haiku, sonnet, opus).

What each policy does

Policy	Effect
`recommended`	Per-command mapping: `status`/`report`/`update`/`install-deps` → haiku · `sync`/`help`/`promote`/`codegen`/`regression`/`work` → opus. Matches v0.11.5 baseline. Recommended default.
`all-opus`	Every command uses opus. Highest quality, highest cost.
`all-sonnet`	Every command uses sonnet. Balanced.
`all-haiku`	Every command uses haiku. Lowest cost; some reasoning-heavy commands may degrade.
`session-default`	Removes the `model:` line entirely. Each command runs on whatever model the current Claude Code session is using.

Step 1 — Resolve the chosen policy

If $ARGUMENTS is exactly one of recommended, all-opus, all-sonnet, all-haiku, session-default, treat that as the chosen policy and skip to Step 2.

Otherwise, fire AskUserQuestion with these 5 options (the first is the shipped default — put it first in the list):

Question: "Which model policy do you want for SCV commands?"
options:
[1] "session-default (Recommended — the shipped default)"
    description: "No model: lines at all. Every SCV command runs on the model your Claude Code session already uses — pick Fable, Opus, or anything else once, and SCV never changes it. This is what a fresh install does."
[2] "recommended"
    description: "Per-command mapping to save cost: status/report/update/install-deps run on haiku; sync/help/promote/codegen/regression/work run on opus. Note: help runs every turn, so this switches your session to opus on nearly every turn."
[3] "all-opus"
    description: "Every SCV command uses opus. Highest quality, significantly higher cost."
[4] "all-sonnet"
    description: "Every SCV command uses sonnet. A middle ground if you want one fixed model for SCV."
[5] "all-haiku"
    description: "Every SCV command uses haiku. Lowest cost; reasoning-heavy commands (work, codegen, promote) may degrade."

Read the full file on GitHub · 116 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +1 lines · +25 tokens per session f8854f4b0085
4d ago First seen · 115 lines · 63 tokens per session scan B 24d9a3be4ee9

Subscribe to this mod's changes

set-models is a command published in the GitHub repository wookiya1364/scv-claude-code (7 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,647 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI claude-code discord plugin regression-testing slack slash-commands

set-models

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

/scv:set-models

Language preference

What each policy does

Step 1 — Resolve the chosen policy

What this file has done since we first saw it

Other commands, from other repositories

caspian-email

caspian-connect-email

caspian-connect-discord

caspian-connect-telegram

caspian-discord

caspian-inbox