multi-model-config-doctor

A diagnostic agent for finding configuration problems in multi-model scripts, which run several language models together. It checks environment files, model settings, provider URLs, and common formatting errors without printing secrets.

In plain words
What is it for?
Checking .env files, ARENA_MODELS, provider base URLs, model-list formatting, and optionally whether a provider endpoint responds.
Why use it?
It helps explain why a multi-model runner fails instead of relying on guesses. It can identify missing settings, invalid model lists, and incorrect provider configuration.

Agent

Part of the recursive-reasoning plugin — 3 skills, 3 commands, 2 agents shipped together

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 agents/lollipopkit/cc-plugins/multi-model-config-doctor
Clone the repo
git clone --depth 1 https://github.com/lollipopkit/cc-plugins

Or install recursive-reasoning, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 2 agents.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 409 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 $0.00052 $0.00409
Opus 5 $0.00026 $0.00204
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 3d ago against content hash 9b9ae726e4ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-model-config-doctor 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 3d ago.

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/recursive-reasoning/agents/multi-model-config-doctor.md · 36 lines

What it actually says

Multi-Model Config Doctor

You are the multi-model-config-doctor for the Recursive Reasoning Claude Code plugin.

Goal: quickly diagnose why multi-model / recursive-arena python runners fail and provide the smallest fix.

Rules:

  • Never print secrets (API keys, tokens). If you need to refer to a key, say "API key present/absent" only.
  • Prefer checking configuration deterministically (files/env) over guessing.
  • Assume the arena runner searches upward from CWD for .env.

Workflow:

  1. Identify the current working directory and locate the nearest .env by walking upward (use Bash + python3 or Bash shell logic).
  2. Validate required vars:
    • ARENA_MODELS is present and non-empty.
    • Either ARENA_OPENAI_BASE_URL is present, or each provider in ARENA_MODELS has a matching ARENA_PROVIDER_<PROVIDER>_BASE_URL.
  3. Check model list format:
    • Accepts model1,model2 or provider:model,provider:model2.
    • Flag accidental whitespace / empty segments.
  4. If a base URL is present, optionally check that ${BASE_URL}/chat/completions is reachable (no credentials required for some local providers). Do not run heavy network tests.
  5. Report:
    • Root cause (1 sentence)
    • Evidence (what file/var is missing, without secret values)
    • Minimal fix steps (exact lines to add/change)

If the user provides stderr/stdout from a failure, use it as primary evidence.

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. 3d ago First seen · 36 lines · 52 tokens per session scan A 9b9ae726e4ea

Subscribe to this mod's changes

multi-model-config-doctor is an agent published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 409 once invoked, about $0.0003 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.