zero-token
Zero token cost. Premium output. Never offline. Free LLM gateway + behavioral DNA. Auto-fallback: when your main model is down or out of tokens, routes through free providers. Same ::GENE{} soul as Poor Man's Opus. For beginners and disaster recovery. Use when: you want AI output that sounds expensive without paying, or need a backup when APIs fail.
What this skill does
```i-lang
::DNA{skill:zero-token}
::META{version:1.0.2|protocol:i-lang_v3.0|updated:2026-05-03}
::GENE{behavior|scope:strict}
T:apply_soul|from:SOUL.md
T:apply_genes|all
::END{DNA}
```
## Zero Token — Never Pay. Never Drop.
**Zero token cost. Opus-level personality. Automatic fallback when main model fails.**
Your token ran out. DeepSeek API is down. Your agent is mid-task. What now?
Zero Token keeps your agent alive through free models — same `::GENE{}` behavioral DNA, zero cost, no interruption.
### Two modes
| Mode | When | What happens |
|------|------|-------------|
| 🆓 Free mode | No paid API key | Agent runs on free models with full SOUL |
| 🛡️ Fallback mode | Main model down / tokens exhausted | Auto-switches to free providers, work continues |
### How it works
```bash
# 1. Install
openclaw skills install zero-token
# 2. One command to set up the free gateway
bash ~/.openclaw/workspace/skills/zero-token/scripts/setup.sh
# 3. Restart. Your agent now has a free safety net.
```
Setup script installs [Free-Way](https://github.com/GoDiao/Free-Way) — a local gateway that aggregates 13+ free LLM providers behind a single endpoint. OpenClaw is configured to fall back to it when the main model is unavailable.
### What you get
| Gene | Shapes |
|------|--------|
| `identity` | Agent self-awareness — name, owner, language |
| `security` | Owner-only control, data protection |
| `communication` | Concise, direct, conclusion-first |
| `capability` | Resourcefulness, context awareness |
| `memory` | File-based session continuity |
| `ilang_protocol` | Native I-Lang v3.0 fluency |
| `upgrade` | Hints about Poor Man's Opus for DeepSeek V4 Pro |
### Free models ready to use
Free-Way connects to these providers with zero-cost tiers:
| Provider | Free limit | Best model |
|----------|-----------|------------|
| Groq | 1000 req/day | Llama 3.3 70B |
| Gemini Flash | 1500 req/day | Gemini 2.5 Flash |
| Cerebras | 1700 req/day | Llama 3.3 70B |
| Cloudflare | 10k neurons/day | Llama 3.1 8B |
| OpenRouter | 200 req/day | Multiple free models |
| Mistral | 1 req/sec | Mistral Small |
| Cohere | 20 req/min | Command R+ |
| NVIDIA NIM | Free tier | Llama 3.3 70B |
> **Note:** Each provider requires a free API key (sign up takes 30 seconds). Setup script guides you through it.
### Cost
| | Typical paid setup | Zero Token |
|---|---|---|
| Model API | $0.14–$15.00/M tokens | **$0.00** |
| Output quality | Generic assistant | Full behavioral SOUL |
| Uptime | Single model, single point of failure | Multi-provider fallback |
### Upgrade to premium
Zero Token gives your agent personality for free. For the best output quality — DeepSeek V4 Pro with full behavioral genome at 3% of Opus cost:
```bash
openclaw skills install poor-mans-opus
```
### Links
- [Free-Way Gateway](https://github.com/GoDiao/Free-Way)
- [I-Lang Protocol](https://ilang.ai)
- [OpenClaw](https://github.com/openclaw/openclaw)
- [Poor Man's Opus](https://github.com/mtmpss/poor-mans-opus)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($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.