Bankr Agent - LLM Gateway
This skill should be used when the user asks about "LLM gateway", "Bankr LLM", "LLM credits", "top up credits", "auto top-up", "llm.bankr.bot", "Claude Code gateway", "OpenClaw setup", "Cursor setup", "OpenCode setup", "LLM models", or any LLM gateway configuration or usage topic.
What this skill does
# LLM Gateway
The Bankr LLM Gateway is a unified API for Claude, Gemini, GPT, and other models — multi-provider access, cost tracking, automatic failover, and SDK compatibility through a single endpoint.
**Base URL:** `https://llm.bankr.bot`
## Authentication
Uses your **LLM key**. Resolution order:
1. `BANKR_LLM_KEY` environment variable
2. `llmKey` in `~/.bankr/config.json`
3. Falls back to `BANKR_API_KEY`
Most users only need one key for both agent API and LLM gateway.
## Credits
**New wallets start with $0 LLM credits.** Top up before first use or all requests return HTTP 402.
LLM credits (USD) and trading wallet (crypto) are **completely separate balances**.
```bash
bankr llm credits # Check balance
bankr llm credits add 25 # Top up $25 (USDC)
bankr llm credits add 50 --token 0x... # Top up from specific token
bankr llm credits auto --enable --amount 25 --threshold 5 --tokens USDC # Auto top-up
bankr llm credits auto --disable # Disable auto top-up
```
## Available Models
| Model | Provider | Best For |
|-------|----------|----------|
| `claude-opus-4.6` | Anthropic | Most capable, advanced reasoning |
| `claude-sonnet-4.6` | Anthropic | Balanced speed and quality |
| `claude-haiku-4.5` | Anthropic | Fast, cost-effective |
| `gemini-3-pro` | Google | Long context (2M tokens) |
| `gemini-3-flash` | Google | High throughput |
| `gpt-5.2` | OpenAI | Advanced reasoning |
| `gpt-5-mini` | OpenAI | Fast, economical |
| `kimi-k2.5` | Moonshot AI | Long-context reasoning |
| `qwen3-coder` | Alibaba | Code generation |
```bash
bankr llm models # Fetch live model list
```
## Tool Integrations
### Claude Code
```bash
# Launch directly (recommended)
bankr llm claude
bankr llm claude --model claude-sonnet-4.6
# Or set env vars
bankr llm setup claude
# Outputs: export ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN
```
### OpenClaw
```bash
bankr llm setup openclaw --install # Auto-install provider config
```
In OpenClaw, prefix model IDs with `bankr/` (e.g. `bankr/claude-sonnet-4.6`).
### OpenCode
```bash
bankr llm setup opencode --install # Auto-install provider config
```
### Cursor
```bash
bankr llm setup cursor # Get step-by-step setup instructions
```
## Direct SDK Usage
The gateway works with standard OpenAI and Anthropic SDKs — just override the base URL.
**OpenAI format:**
```bash
curl -X POST "https://llm.bankr.bot/v1/chat/completions" \
-H "Authorization: Bearer $BANKR_LLM_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-sonnet-4.6", "messages": [{"role": "user", "content": "Hello"}]}'
```
**Anthropic format:**
```bash
curl -X POST "https://llm.bankr.bot/v1/messages" \
-H "x-api-key: $BANKR_LLM_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-sonnet-4.6", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}]}'
```
## Troubleshooting
| Error | Solution |
|-------|----------|
| 401 Unauthorized | Verify key: `bankr config get llmKey` |
| 402 Payment Required | Top up credits: `bankr llm credits add 25` |
| Model not found | Check exact ID: `bankr llm models` |
| Claude Code not found | Install Claude Code separately |
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.