setup

A command that configures and saves API keys for supported providers in a local Claude settings file.

In plain words
What is it for?
Adding or updating Zai, Kimi, and Minimax API keys, setting the file's permissions, and confirming which providers are ready.
Why use it?
It keeps provider credentials in one protected file so the user can switch between configured services later.

Command

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/kossakovsky/cc-plugins/setup
Clone the repo
git clone --depth 1 https://github.com/kossakovsky/cc-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 281 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.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.00281
Opus 5 $0.00003 $0.00140
Sonnet 5 $0.00001 $0.00056
Haiku 4.5 $0.00001 $0.00028

Measured yesterday against content hash 6e6dc408c378, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

5. **Set permissions** using Bash: `chmod 600 ~/.claude/provider-keys.json`
plugins/switch-provider/commands/setup.md · 34 lines

What it actually says

Setup Provider Keys

Configure and save API keys for providers to ~/.claude/provider-keys.json.

Steps

  1. Read existing keys from ~/.claude/provider-keys.json if the file exists (use Read tool, handle file not found gracefully)

  2. Determine which provider to configure:

    • If an argument was provided (e.g., zai), configure that provider
    • If no argument, ask the user which provider(s) they want to configure. Options: zai, kimi, minimax
  3. For each provider to configure:

    • Ask the user for their API key
    • Add or update the key in the keys object under the provider name
  4. Write the updated keys to ~/.claude/provider-keys.json:

    {
      "zai": "key-here",
      "kimi": "sk-key-here",
      "minimax": "key-here"
    }
    
  5. Set permissions using Bash: chmod 600 ~/.claude/provider-keys.json

  6. Confirm which providers were configured and remind the user they can now switch with /switch-provider:<provider>

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 · 7 tokens per session scan B 6e6dc408c378

Subscribe to this mod's changes

setup is a command published in the GitHub repository kossakovsky/cc-plugins (3 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 281 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.