agentmods.dev

settings

A command for viewing or changing which AI providers are enabled, which one is the default, and which providers are compared together.

In plain words
What is it for?
Use it to enable or disable providers, choose the default, or change the set used by the comparison command.
Why use it?
It avoids manually editing provider settings and makes the assistant's AI-provider choices explicit.

Command

4 4mo ago A scan 19 tokens original Apache-2.0
View the source file dysfunc/ai-plugins-cc
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/dysfunc/ai-plugins-cc/settings
Clone the repo
git clone --depth 1 https://github.com/dysfunc/ai-plugins-cc
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00437
Opus 5 $0.00010 $0.00218
Sonnet 5 $0.00004 $0.00087
Haiku 4.5 $0.00002 $0.00044

Measured yesterday against content hash 9825a24c586c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

settings scanned grade A with 0 findings 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/ai/commands/settings.md · 34 lines

What it actually says

If the user passed a subcommand in $ARGUMENTS, run it directly:

node "${CLAUDE_PLUGIN_ROOT}/scripts/ai-companion.mjs" settings $ARGUMENTS --json

Surface the JSON's message field to the user. If the call exits non-zero, show error.

If $ARGUMENTS is empty, drive the interactive flow:

  1. Run node "${CLAUDE_PLUGIN_ROOT}/scripts/ai-companion.mjs" settings show --json to read current state.
  2. Show a short status block: enabled providers, default, compare set.
  3. Use AskUserQuestion (single choice) to ask what they want to do:
    • "Enable a provider"
    • "Disable a provider"
    • "Change default provider"
    • "Change /ai:compare set"
    • "Done"
  4. Based on the choice, ask for the provider id(s) (use AskUserQuestion again with the registered providers as options), then run the matching subcommand:
    • settings enable <id> / disable <id> / set-default <id> / set-compare <id,id,...>
  5. Loop back to step 1 until the user picks "Done".

Hard rules

  • Never enable a provider that's not in knownProviders from settings show --json. The companion will reject it; surface its error verbatim if the user insisted.
  • Disabling the current default reassigns the default to the first remaining enabled provider (this is automatic in the companion). Tell the user this happened.
  • If the user wants to enable a provider that isn't yet ready (CLI missing, no auth), suggest running /ai:setup instead of trying to enable it here.
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.

  1. yesterday First seen · 34 lines · 19 tokens per session scan A 9825a24c586c

Subscribe to this mod's changes

settings is a command published in the GitHub repository dysfunc/ai-plugins-cc (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 437 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

claudeclaude-codeclaude-code-plugincodexgeminigrok
Related

Other commands, from other repositories

ask

Query multiple AI agents (Gemini, OpenAI, Grok, Perplexity, Kimi, and a local ollama model) for diverse perspectives on architecture decisions, technology choices, debugging dead-ends, and security tradeoffs. Use this whenever the user names the council directly, whatever the topic — ask the council, council review…

hex/claude-council · 189 tokens

result

Fetch, list, or cancel background council jobs started with --async.

hex/claude-council · 13 tokens

status

Check connectivity and configuration status of all council providers.

hex/claude-council · 9 tokens

grok-files

List, prune, or gc Grok (xAI) uploaded files. Cleanup for bridge-owned uploads only.

antonbabenko/deliberation · 26 tokens

help

Show how to use deliberation here - what each command does, when to reach for it, and real prompts you can paste right now. Read-only.

antonbabenko/deliberation · 33 tokens

setup

Configure deliberation with Codex (GPT), Gemini, Grok, and OpenRouter MCP servers.

antonbabenko/deliberation · 21 tokens