Provider Integration
hex/claude-council
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface.
Reference guide for using external AI models via claudish CLI.
Install Proxy Mode Reference
$ npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MadAppGang/claude-code proxy-mode-reference --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/multimodel/skills/proxy-mode-reference .claude/skills/proxy-mode-reference && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "proxy-mode-reference" agent skill from https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/proxy-mode-reference into .claude/skills/proxy-mode-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-mode-reference", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/proxy-mode-referenceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MadAppGang/claude-code proxy-mode-reference --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/multimodel/skills/proxy-mode-reference .agents/skills/proxy-mode-reference && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "proxy-mode-reference" agent skill from https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/proxy-mode-reference into .agents/skills/proxy-mode-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-mode-reference", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MadAppGang/claude-code proxy-mode-reference --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/multimodel/skills/proxy-mode-reference .cursor/skills/proxy-mode-reference && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "proxy-mode-reference" agent skill from https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/proxy-mode-reference into .cursor/skills/proxy-mode-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-mode-reference", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MadAppGang/claude-code.git --path plugins/multimodel/skills/proxy-mode-reference--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MadAppGang/claude-code proxy-mode-reference --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/multimodel/skills/proxy-mode-reference .gemini/skills/proxy-mode-reference && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "proxy-mode-reference" agent skill from https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/proxy-mode-reference into .gemini/skills/proxy-mode-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-mode-reference", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MadAppGang/claude-code proxy-mode-referenceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/multimodel/skills/proxy-mode-reference .github/skills/proxy-mode-reference && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "proxy-mode-reference" agent skill from https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/proxy-mode-reference into .github/skills/proxy-mode-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-mode-reference", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MadAppGang/claude-code proxy-mode-reference --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/multimodel/skills/proxy-mode-reference .opencode/skills/proxy-mode-reference && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "proxy-mode-reference" agent skill from https://github.com/MadAppGang/claude-code/tree/main/plugins/multimodel/skills/proxy-mode-reference into .opencode/skills/proxy-mode-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-mode-reference", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
proxy-mode-reference- GitHub stars
- 285
- Token cost
- ~1.3k tokens
- SKILL.md length
- 381 words
- Files
- 1
- Skills in repo
- 69
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reference guide for using external AI models via claudish CLI.
- Works in 4 steps: Detect context from task keywords… → If contextPreferences[context] exists →… → If empty (first time) → ASK user → SAVE… → …
- Running multi-model reviews
- SKILL.md covers ⚠️ Learn and Reuse Model…, How External Models Work, Invoking External Models and Multi-Backend Routing, plus 3 more sections
- Calls npm; needs OPENROUTER_API_KEY and GEMINI_API_KEY
What it does
Proxy Mode Reference is an agent skill from MadAppGang/claude-code. Reference guide for using external AI models via claudish CLI. Use when running multi-model reviews, understanding how /team invokes external models, or debugging external model integration issues. Includes routing prefixes for MiniMax, Kimi, GLM direct APIs.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Model routing and gateways. It works with Kimi, MiniMax, OpenAI and OpenRouter. The repository describes itself as: claude code plugins marketplace. The licence is MIT.
When your agent uses it
- Running multi-model reviews
- Understanding how /team invokes external models
- Debugging external model integration issues
Example prompts
- “/proxy-mode-reference”
Requirements
- Node.js
- A credential in OPENROUTER_API_KEY
- A credential in GEMINI_API_KEY
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Detect context from task keywords (debug/research/coding/review)
- If contextPreferences[context] exists → USE IT (no asking)
- If empty (first time) → ASK user → SAVE for that context
- User says "change models" → UPDATE preferences
What it can do on your machine
Read from SKILL.md and the folder at commit 6097ad4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
OPENROUTER_API_KEYGEMINI_API_KEYOPENAI_API_KEYMINIMAX_API_KEYKIMI_API_KEYGLM_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Proxy Mode Reference loads about 1.3k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 381 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from MadAppGang/claude-code at commit 6097ad4, republished under its MIT licence (© MadAppGang). 381 words, ~1,304 tokens.
Download SKILL.mdSave it as
.claude/skills/proxy-mode-reference/SKILL.md (or your agent's skills folder).- name
- proxy-mode-reference
- description
- Reference guide for using external AI models via claudish CLI. Use when running multi-model reviews, understanding how /team invokes external models, or debugging external model integration issues. Includes routing prefixes for MiniMax, Kimi, GLM direct APIs.
- version
- 2.0.0
- keywords
- external-models, multi-model, claudish, routing-prefixes, minimax, kimi, glm, gemini, openai, bash-claudish
- plugin
- multimodel
- updated
- 2026-02-11
External Models via Claudish CLI — Reference Guide
⚠️ Learn and Reuse Model Preferences
Models are learned per context and reused automatically:
cat .claude/multimodel-team.json 2>/dev/null- Detect context from task keywords (debug/research/coding/review)
- If
contextPreferences[context]exists → USE IT (no asking) - If empty (first time) → ASK user → SAVE for that context
- User says "change models" → UPDATE preferences
How External Models Work
External models are invoked deterministically via the claudish CLI. The orchestrator
(e.g., /team command) calls claudish directly through Bash — no LLM delegation needed.
Orchestrator → Bash(claudish --model {MODEL_ID} --stdin) → External ModelThis approach is 100% reliable because it's a direct CLI invocation, not a prompt-based delegation.
Invoking External Models
From /team Command (Automatic)
The /team command handles this automatically:
- Internal models → Task(dev:researcher)
- External models → Bash(claudish --model {MODEL_ID} --stdin)
Direct CLI Usage
# Pattern
claudish --model {MODEL_ID} --stdin --quiet < prompt-file.md > result.md
# Examples
claudish --model x-ai/grok-code-fast-1 --stdin --quiet < task.md > grok-result.md
claudish --model google/gemini-3-pro-preview --stdin --quiet < task.md > gemini-result.mdRequired flags:
--model— The external model to use--stdin— Read prompt from stdin (for large prompts)--quiet— Suppress log messages (for clean output capture)
Multi-Backend Routing
Claudish routes to different backends based on model ID prefix:
| Prefix | Backend | Required Key | Example |
|---|---|---|---|
| (none) | OpenRouter | OPENROUTER_API_KEY | openai/gpt-5.2 |
g/ gemini/ | Google Gemini API | GEMINI_API_KEY | g/gemini-2.0-flash |
oai/ | OpenAI Direct API | OPENAI_API_KEY | oai/gpt-4o |
mmax/ mm/ | MiniMax Direct API | MINIMAX_API_KEY | mmax/MiniMax-M2.1 |
kimi/ moonshot/ | Kimi Direct API | KIMI_API_KEY | kimi/kimi-k2-thinking-turbo |
glm/ zhipu/ | GLM Direct API | GLM_API_KEY | glm/glm-4.7 |
ollama/ | Ollama (local) | None | ollama/llama3.2 |
lmstudio/ | LM Studio (local) | None | lmstudio/qwen |
vllm/ | vLLM (local) | None | vllm/model |
mlx/ | MLX (local) | None | mlx/model |
http://... | Custom endpoint | None | http://localhost:8000/model |
Show full SKILL.md (156 more words)Show less
⚠️ Prefix Collision Warning
OpenRouter model IDs may collide with routing prefixes. Check the prefix table above.
Collision-free models (safe for OpenRouter):
x-ai/grok-*✅deepseek/*✅minimax/*✅ (usemmax/for MiniMax Direct)qwen/*✅mistralai/*✅moonshotai/*✅ (usekimi/for Kimi Direct)anthropic/*✅z-ai/*✅ (useglm/for GLM Direct)google/*✅ (useg/for Gemini Direct)openai/*✅ (useoai/for OpenAI Direct)
Direct API prefixes for cost savings:
| OpenRouter Model | Direct API Prefix | Notes |
|---|---|---|
openai/gpt-* | oai/gpt-* | OpenAI Direct API |
google/gemini-* | g/gemini-* | Gemini Direct API |
minimax/* | mmax/* or mm/* | MiniMax Direct API |
moonshotai/* | kimi/* or moonshot/ | Kimi Direct API |
z-ai/glm-* | glm/* or zhipu/* | GLM Direct API |
Correct Usage Patterns
Single External Model
claudish --model x-ai/grok-code-fast-1 --stdin --quiet < task.md > result.mdParallel External Models (in /team)
# All launched in a single message with run_in_background: true
Bash("claudish --model x-ai/grok-code-fast-1 --stdin --quiet < vote-prompt.md > grok-result.md 2>grok-stderr.log; echo $? > grok.exit")
Bash("claudish --model google/gemini-3-pro-preview --stdin --quiet < vote-prompt.md > gemini-result.md 2>gemini-stderr.log; echo $? > gemini.exit")Verifying Results
# Check exit code
cat grok.exit # 0 = success
# Check output size
wc -c < grok-result.md # Should be >50 bytes
# Check stderr for errors
cat grok-stderr.logCommon Mistakes
Mistake 1: Not capturing exit code
# ❌ WRONG - no way to detect failures
claudish --model grok --stdin < task.md > result.md
# ✅ CORRECT - capture exit code
claudish --model grok --stdin < task.md > result.md 2>stderr.log; echo $? > result.exitTroubleshooting
"claudish: command not found"
Fix: npm install -g claudish
"OPENROUTER_API_KEY not set"
Fix: export OPENROUTER_API_KEY=your-key
Non-zero exit code
Fix: Check stderr log for error details. Common causes: rate limits, invalid model ID, API key issues.
© MadAppGang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/multimodel/skills/proxy-mode-reference of MadAppGang/claude-code.
Open the folder on GitHubat commit 6097ad4
Compare with similar skills
Proxy Mode Reference next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Proxy Mode Reference this skillMadAppGang/claude-code | 285 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Provider Integrationhex/claude-council | 851 | — | ~635 | Automated safety check: Pass | MIT | |
| New Providerfinch-xu/cc-router | 272 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Configuring Visionoxbshw/watch-skill | 469 | — | ~509 | Automated safety check: Notes | MIT | |
| QuorumDetrol/quorum-cli | 119 | — | ~807 | Automated safety check: Notes | Custom licence | |
| LLM GatewayBagelHole/DevOps-Security-Agent-Skills | 1.1k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
New Provider
finch-xu/cc-router
用于在 cc-router 仓库新增一个 LLM provider（即在 src-tauri/providers/ 下添加 YAML 描述符并完成配套的同步改动）。当用户说「加 provider」「接入 XX 厂商」「新增订阅源」「provider YAML」「让 cc-router 支持 OpenRouter/Together/Groq/Ollama 之类」时必须触发本…
Configuring Vision
oxbshw/watch-skill
The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models.
Quorum
Detrol/quorum-cli
Run a structured debate between agent CLIs (claude, codex, agy, grok) and the user's configured API or local models (OpenAI, Anthropic, Google, xAI, OpenRouter, Ollama and more) through the Quorum…
LLM Gateway
BagelHole/DevOps-Security-Agent-Skills
Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking.
Reasoning Serialization Tests
tailcallhq/forgecode
Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests.
More from MadAppGang/claude-code
All 69 skills in this repoContent Brief
MadAppGang/claude-code
Content brief template and creation methodology for SEO-optimized content.
Context Detection
MadAppGang/claude-code
A skill your agent uses when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g…
Content Optimizer
MadAppGang/claude-code
On-page SEO optimization techniques including keyword density, meta tags, heading structure, and readability.
Keyword Cluster Builder
MadAppGang/claude-code
Techniques for expanding seed keywords and clustering by topic and intent.
Serp Analysis
MadAppGang/claude-code
SERP analysis techniques for intent classification, feature identification, and competitive intelligence.
Agent Coordination Discipline
MadAppGang/claude-code
A skill your agent uses when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents.
Related
Categories
Questions about Proxy Mode Reference
What does Proxy Mode Reference do?
Reference guide for using external AI models via claudish CLI. Proxy Mode Reference is an agent skill from MadAppGang/claude-code. Reference guide for using external AI models via claudish CLI.
When should I use Proxy Mode Reference?
Proxy Mode Reference fits situations like: running multi-model reviews; understanding how /team invokes external models; debugging external model integration issues.
How do I install Proxy Mode Reference in Claude Code?
Run `npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a claude-code`. Or copy the skill folder (plugins/multimodel/skills/proxy-mode-reference in MadAppGang/claude-code) into .claude/skills/proxy-mode-reference in your project. Claude Code loads it when a task matches its description.
How do I install Proxy Mode Reference in Codex?
Run `npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a codex`. Or copy the skill folder (plugins/multimodel/skills/proxy-mode-reference in MadAppGang/claude-code) into .agents/skills/proxy-mode-reference in your project. Codex loads it when a task matches its description.
Can I use Proxy Mode Reference in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MadAppGang/claude-code --skill proxy-mode-reference -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/proxy-mode-reference, .gemini/skills/proxy-mode-reference, .github/skills/proxy-mode-reference and .opencode/skills/proxy-mode-reference in your project.
What does Proxy Mode Reference need to run?
Going by SKILL.md and its folder, Proxy Mode Reference needs the command-line tools its instructions call (npm) and credentials named OPENROUTER_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY and MINIMAX_API_KEY. Our summary lists: Node.js; A credential in OPENROUTER_API_KEY; A credential in GEMINI_API_KEY.
Does Proxy Mode Reference access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Proxy Mode Reference safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Proxy Mode Reference use?
Proxy Mode Reference is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Proxy Mode Reference use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Proxy Mode Reference?
Skills that share tags, products or a category with Proxy Mode Reference: Provider Integration (hex/claude-council, 851 stars), New Provider (finch-xu/cc-router, 272 stars), Configuring Vision (oxbshw/watch-skill, 469 stars) and Quorum (Detrol/quorum-cli, 119 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Proxy Mode Reference?
MadAppGang (a GitHub organization) maintains it in MadAppGang/claude-code, which has 285 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on March 15, 2026.
Source: MadAppGang/claude-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.