deepclaude-proxy
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend at up to 17x lower cost.
What this skill does
# deepclaude
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
**deepclaude** routes Claude Code's API calls to DeepSeek V4 Pro, OpenRouter, Fireworks AI, or any Anthropic-compatible backend — keeping the full Claude Code UX (file editing, bash, subagents, git) while cutting costs by up to 17x.
## How it works
Claude Code reads specific environment variables to determine its API endpoint and model names. `deepclaude` sets these per-session (not permanently), launches Claude Code, then restores originals on exit.
```
Your terminal
└── Claude Code CLI (tool loop, file editing, bash, git — unchanged)
└── API calls → DeepSeek V4 Pro ($0.87/M) instead of Anthropic ($15/M)
```
Key environment variables Claude Code uses:
| Variable | Purpose |
|---|---|
| `ANTHROPIC_BASE_URL` | API endpoint override |
| `ANTHROPIC_AUTH_TOKEN` | API key for the backend |
| `ANTHROPIC_DEFAULT_OPUS_MODEL` | Model for Opus-tier tasks |
| `ANTHROPIC_DEFAULT_SONNET_MODEL` | Model for Sonnet-tier tasks |
| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | Model for Haiku-tier / subagents |
| `CLAUDE_CODE_SUBAGENT_MODEL` | Model for spawned subagents |
## Installation
### Prerequisites
- Claude Code CLI installed (`npm install -g @anthropic-ai/claude-code`)
- Node.js 18+ (for the proxy server)
- API key for at least one backend
### 1. Clone the repo
```bash
git clone https://github.com/aattaran/deepclaude.git
cd deepclaude
```
### 2. Set API keys
**macOS/Linux:**
```bash
# DeepSeek (default backend — get key at platform.deepseek.com)
echo 'export DEEPSEEK_API_KEY="$DEEPSEEK_API_KEY"' >> ~/.bashrc
# OpenRouter (optional — cheapest US latency)
echo 'export OPENROUTER_API_KEY="$OPENROUTER_API_KEY"' >> ~/.bashrc
# Fireworks AI (optional — fastest inference)
echo 'export FIREWORKS_API_KEY="$FIREWORKS_API_KEY"' >> ~/.bashrc
source ~/.bashrc
```
**Windows (PowerShell):**
```powershell
setx DEEPSEEK_API_KEY $env:DEEPSEEK_API_KEY
setx OPENROUTER_API_KEY $env:OPENROUTER_API_KEY
setx FIREWORKS_API_KEY $env:FIREWORKS_API_KEY
```
### 3. Install the CLI
**macOS/Linux:**
```bash
chmod +x deepclaude.sh
sudo ln -s "$(pwd)/deepclaude.sh" /usr/local/bin/deepclaude
```
**Windows (PowerShell):**
```powershell
Copy-Item deepclaude.ps1 "$env:USERPROFILE\.local\bin\deepclaude.ps1"
# Or add repo directory to PATH:
setx PATH "$env:PATH;C:\path\to\deepclaude"
```
## Key CLI commands
```bash
# Launch Claude Code with DeepSeek V4 Pro (default)
deepclaude
# Show available backends and configured API keys
deepclaude --status
# Select a specific backend
deepclaude --backend ds # DeepSeek (default)
deepclaude --backend or # OpenRouter
deepclaude --backend fw # Fireworks AI
deepclaude --backend anthropic # Normal Claude Opus
# Show pricing comparison
deepclaude --cost
# Latency benchmark across all configured providers
deepclaude --benchmark
# Switch backend mid-session (proxy must be running)
deepclaude --switch ds
deepclaude --switch or
deepclaude --switch anthropic
# Remote control — open session in any browser
deepclaude --remote
deepclaude --remote --backend or
deepclaude --remote --backend anthropic
```
## Supported backends
| Backend | Flag | Input/M | Output/M | Notes |
|---|---|---|---|---|
| DeepSeek | `ds` | $0.44 | $0.87 | Auto context caching (120x cheaper on repeat turns) |
| OpenRouter | `or` | $0.44 | $0.87 | Lowest latency from US/EU |
| Fireworks AI | `fw` | $1.74 | $3.48 | Fastest inference, US servers |
| Anthropic | `anthropic` | $3.00 | $15.00 | Original Claude Opus |
## Live backend switching (no restart)
A local proxy runs on `localhost:3200` and intercepts all API calls. Switch backends instantly without restarting Claude Code.
### Proxy control endpoints
```bash
# Switch backend
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=deepseek"
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=openrouter"
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=anthropic"
# Check current backend + uptime
curl -s http://127.0.0.1:3200/_proxy/status
# Token usage and cost savings vs Anthropic
curl -s http://127.0.0.1:3200/_proxy/cost
```
Cost endpoint response shape:
```json
{
"backends": {
"deepseek": {
"input_tokens": 125000,
"output_tokens": 45000,
"requests": 12,
"cost": 0.0941,
"anthropic_equivalent": 1.05
}
},
"total_cost": 0.0941,
"anthropic_equivalent": 1.05,
"savings": 0.9559
}
```
### Slash commands (recommended UX)
Create files in `~/.claude/commands/` to switch backends from inside any Claude Code session:
**`~/.claude/commands/deepseek.md`:**
```markdown
Switch the model proxy to DeepSeek. Run this command silently and report the result:
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=deepseek"
If successful, say: "Switched to DeepSeek."
```
**`~/.claude/commands/anthropic.md`:**
```markdown
Switch the model proxy back to Anthropic. Run this command silently and report the result:
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=anthropic"
If successful, say: "Switched to Anthropic."
```
**`~/.claude/commands/openrouter.md`:**
```markdown
Switch the model proxy to OpenRouter. Run this command silently and report the result:
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=openrouter"
If successful, say: "Switched to OpenRouter."
```
Then type `/deepseek`, `/anthropic`, or `/openrouter` in any Claude Code session.
### VS Code keyboard shortcuts
**`.vscode/tasks.json`:**
```json
{
"version": "2.0.0",
"tasks": [
{
"label": "Proxy: Switch to DeepSeek",
"type": "shell",
"command": "curl -sX POST http://127.0.0.1:3200/_proxy/mode -d 'backend=deepseek'",
"presentation": { "reveal": "always" },
"problemMatcher": []
},
{
"label": "Proxy: Switch to Anthropic",
"type": "shell",
"command": "curl -sX POST http://127.0.0.1:3200/_proxy/mode -d 'backend=anthropic'",
"presentation": { "reveal": "always" },
"problemMatcher": []
},
{
"label": "Proxy: Switch to OpenRouter",
"type": "shell",
"command": "curl -sX POST http://127.0.0.1:3200/_proxy/mode -d 'backend=openrouter'",
"presentation": { "reveal": "always" },
"problemMatcher": []
}
]
}
```
**`keybindings.json`:**
```json
[
{ "key": "ctrl+alt+d", "command": "workbench.action.tasks.runTask", "args": "Proxy: Switch to DeepSeek" },
{ "key": "ctrl+alt+a", "command": "workbench.action.tasks.runTask", "args": "Proxy: Switch to Anthropic" },
{ "key": "ctrl+alt+o", "command": "workbench.action.tasks.runTask", "args": "Proxy: Switch to OpenRouter" }
]
```
## VS Code / Cursor terminal profiles
**`settings.json` on macOS/Linux:**
```json
{
"terminal.integrated.profiles.linux": {
"DeepSeek Agent": {
"path": "/usr/local/bin/deepclaude"
},
"DeepSeek (OpenRouter)": {
"path": "/usr/local/bin/deepclaude",
"args": ["--backend", "or"]
}
},
"terminal.integrated.defaultProfile.linux": "DeepSeek Agent"
}
```
**`settings.json` on Windows:**
```json
{
"terminal.integrated.profiles.windows": {
"DeepSeek Agent": {
"path": "powershell.exe",
"args": ["-ExecutionPolicy", "Bypass", "-NoExit", "-File", "C:\\path\\to\\deepclaude.ps1"]
}
}
}
```
## Remote control (browser UI)
Open a Claude Code session in any browser with DeepSeek as the backend:
```bash
deepclaude --remote # DeepSeek backend
deepclaude --remote --backend or # OpenRouter backend
deepclaude --remote --backend anthropic # Normal Anthropic
```
Traffic split:
```
claude remote-control
├── Bridge WebSocket → wss://bridge.claudeusercontent.com (Anthropic, required)
└── Model API calls → http://localhost:3200 (proxy)
├── /v1/messages → active backend (DeepSeek/OR/etc.)
└── everything else → Anthropic (passthrough)
```
**Requirements for remote control:**
- MustRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.