# Send Freeride Opencode to your agent
Use the source page and any available docs to guide the install because the item currently does not return a direct package file.
## Fast path
- Open the source page via Open source listing.
- If you can obtain the package, extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the source page and extracted files.
## Suggested prompts
### New install

```text
I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. Then review README.md for any prerequisites, environment setup, or post-install checks.
```
### Upgrade existing

```text
I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. Then review README.md for any prerequisites, environment setup, or post-install checks.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "freeride-opencode",
    "name": "Freeride Opencode",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Heldinhow/freeride-opencode",
    "canonicalUrl": "https://clawhub.ai/Heldinhow/freeride-opencode",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/freeride-opencode",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=freeride-opencode",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "PLAN.md",
      "README.md",
      "SKILL.md",
      "SPECIFICATION.md",
      "TASKS.md",
      "examples/usage.md"
    ],
    "downloadMode": "manual_only",
    "sourceHealth": {
      "source": "tencent",
      "slug": "freeride-opencode",
      "status": "source_issue",
      "reason": "not_found",
      "recommendedAction": "review_source",
      "checkedAt": "2026-05-01T15:20:12.750Z",
      "expiresAt": "2026-05-02T15:20:12.750Z",
      "httpStatus": 404,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=freeride-opencode",
      "contentType": "text/plain",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=freeride-opencode",
        "contentDisposition": null,
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "freeride-opencode"
      },
      "scope": "item",
      "summary": "Known item issue.",
      "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.",
      "primaryActionLabel": "Open source listing",
      "primaryActionHref": "https://clawhub.ai/Heldinhow/freeride-opencode"
    },
    "validation": {
      "installChecklist": [
        "Open the source listing and confirm there is a real package or setup artifact available.",
        "Review SKILL.md before asking your agent to continue.",
        "Treat this source as manual setup until the upstream download flow is fixed."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/freeride-opencode",
    "downloadUrl": "https://openagent3.xyz/downloads/freeride-opencode",
    "agentUrl": "https://openagent3.xyz/skills/freeride-opencode/agent",
    "manifestUrl": "https://openagent3.xyz/skills/freeride-opencode/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/freeride-opencode/agent.md"
  }
}
```
## Documentation

### Freeride OpenCode

Configure OpenCode Zen free models with intelligent fallbacks to optimize costs while maintaining reliability.

⚠️ Important: To use this skill, you need two API keys:

OpenCode Zen API key - For OpenCode free models (MiniMax M2.1, Kimi K2.5, GLM 4.7, GPT 5 Nano)
OpenRouter API key - For OpenRouter free models (Trinity Large and other OpenRouter providers)

Configure both keys in your OpenCode/Zen settings before applying these configurations.

### Quick Start

Apply optimal free model configuration with provider diversification:

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "opencode/minimax-m2.1-free",
        "fallbacks": [
          "openrouter/arcee-ai/trinity-large-preview:free",
          "opencode/kimi-k2.5-free"
        ]
      },
      "heartbeat": {
        "model": "opencode/glm-4.7-free"
      },
      "subagents": {
        "model": "opencode/kimi-k2.5-free"
      }
    }
  }
}

### 🔑 API Keys Required

This skill uses models from two different providers, so you need both API keys configured:

### 1. OpenCode Zen API Key

Required for:

opencode/minimax-m2.1-free
opencode/kimi-k2.5-free
opencode/glm-4.7-free
opencode/gpt-5-nano

Where to get: Sign up at OpenCode Zen and generate an API key.

### 2. OpenRouter API Key

Required for:

openrouter/arcee-ai/trinity-large-preview:free
Any other OpenRouter free models you add

Where to get: Sign up at OpenRouter.ai and generate an API key.

### Configuration

Add both keys to your OpenCode configuration:

{
  "providers": {
    "opencode": {
      "api_key": "YOUR_OPENCODE_ZEN_API_KEY"
    },
    "openrouter": {
      "api_key": "YOUR_OPENROUTER_API_KEY"
    }
  }
}

### Fallback Behavior by Provider

If OpenCode models fail → tries next OpenCode fallback or OpenRouter model
If OpenRouter models fail → tries next OpenRouter or OpenCode fallback
Configure both providers for maximum reliability

### Model Selection Guide

See models.md for detailed model comparisons, capabilities, and provider information.

Task TypeRecommended ModelRationalePrimary/GeneralMiniMax M2.1 FreeBest free model capabilityFallback 1Trinity Large FreeDifferent provider (OpenRouter) for rate limit resilienceFallback 2Kimi K2.5 FreeGeneral purpose, balanceHeartbeatGLM 4.7 FreeMultilingual, cost-effective for frequent checksSubtasks/SubagentsKimi K2.5 FreeBalanced capability for secondary tasks

### Free Models Available

ModelIDBest ForMiniMax M2.1 Freeopencode/minimax-m2.1-freeComplex reasoning, coding (Primary)Trinity Large Freeopenrouter/arcee-ai/trinity-large-preview:freeHigh-quality OpenRouter option (Fallback 1)Kimi K2.5 Freeopencode/kimi-k2.5-freeGeneral purpose, balance (Fallback 2)

### Provider Diversification (v1.2.0)

This version implements provider diversification to maximize resilience against rate limits and service disruptions:

"fallbacks": [
  "openrouter/arcee-ai/trinity-large-preview:free",  // Different provider (OpenRouter)
  "opencode/kimi-k2.5-free"                           // Same provider as primary (OpenCode)
]

Why Provider Diversification Matters:

Rate limit isolation: If OpenCode experiences rate limits, OpenRouter models remain available (and vice versa)
First fallback from different provider: Trinity Large on OpenRouter ensures continuity even if all OpenCode models are rate-limited
Maximum resilience: By spreading across providers, you avoid a single point of failure

Fallback triggers:

Rate limits exceeded
Auth failures
Timeouts
Provider unavailability

### Fallback Behavior by Provider

If OpenCode models fail → tries OpenRouter fallback first (Trinity Large), then back to OpenCode (Kimi)
If OpenRouter model fails → tries OpenCode fallback (Kimi)
This cross-provider approach ensures at least one model is usually available

### Heartbeat (Every 30 min)

"heartbeat": {
  "every": "30m",
  "model": "opencode/gpt-5-nano"
}

Use the cheapest model for frequent, lightweight checks.

### Subtasks/Subagents

"subagents": {
  "model": "opencode/kimi-k2.5-free"
}

Good balance for secondary tasks that need reasonable capability.

### Complete Example

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "opencode/minimax-m2.1-free",
        "fallbacks": [
          "openrouter/arcee-ai/trinity-large-preview:free",
          "opencode/kimi-k2.5-free"
        ]
      },
      "models": {
        "opencode/minimax-m2.1-free": { "alias": "MiniMax M2.1" },
        "opencode/kimi-k2.5-free": { "alias": "Kimi K2.5" },
        "openrouter/arcee-ai/trinity-large-preview:free": { "alias": "Trinity Large" }
      },
      "heartbeat": {
        "every": "30m",
        "model": "opencode/glm-4.7-free"
      },
      "subagents": {
        "model": "opencode/kimi-k2.5-free"
      }
    }
  }
}

### Applying Configuration

Use OpenClaw CLI:

openclaw config.patch --raw '{
  "agents": {
    "defaults": {
      "model": {
        "primary": "opencode/minimax-m2.1-free",
        "fallbacks": ["openrouter/arcee-ai/trinity-large-preview:free", "opencode/kimi-k2.5-free"]
      },
      "heartbeat": { "model": "opencode/glm-4.7-free" },
      "subagents": { "model": "opencode/kimi-k2.5-free" }
    }
  }
}'

### Best Practices

Provider diversification - Always have your first fallback from a different provider (e.g., OpenRouter) to avoid rate limits affecting all models
Keep fallbacks minimal - 2-3 well-chosen fallbacks are better than many
Match model to task - Don't use MiniMax for simple checks
Test fallback order - Put more capable models first, with provider diversification
Monitor usage - Track which models get used most

### Troubleshooting

Authentication errors (401/403)?

Check that you have both API keys configured:

OpenCode Zen API key for OpenCode models
OpenRouter API key for Trinity Large and OpenRouter models


Verify keys are valid and have not expired

Rate limits still occurring?

Add provider diversification (ensure first fallback is from different provider)
Consider reducing heartbeat frequency

Responses too slow?

Move GPT 5 Nano higher in fallback chain
Use simpler model for subtasks

Model not available?

Check model ID format: opencode/model-id-free or openrouter/provider/model:free
Verify model is still free (check models.md)
Ensure you have the correct API key for the provider

OpenRouter models not working?

Verify OpenRouter API key is configured
Check OpenRouter account has credits/access
Some models may have additional access requirements

### models.md

Complete reference of all free models with capabilities, providers, performance comparisons, and error handling.

### templates.md

Ready-to-use configuration templates for different use cases (minimal, complete, cost-optimized, performance-optimized).

### examples/usage.md

Practical examples showing how to use this skill in real scenarios.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: Heldinhow
- Version: 1.2.0
## Source health
- Status: source_issue
- Known item issue.
- This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.
- Health scope: item
- Reason: not_found
- Checked at: 2026-05-01T15:20:12.750Z
- Expires at: 2026-05-02T15:20:12.750Z
- Recommended action: Open source listing
## Links
- [Detail page](https://openagent3.xyz/skills/freeride-opencode)
- [Send to Agent page](https://openagent3.xyz/skills/freeride-opencode/agent)
- [JSON manifest](https://openagent3.xyz/skills/freeride-opencode/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/freeride-opencode/agent.md)
- [Download page](https://openagent3.xyz/downloads/freeride-opencode)