# Send Open Router to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "open-router",
    "name": "Open Router",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/open-router",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/open-router",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/open-router",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=open-router",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "auth-and-provider.md",
      "cost-guardrails.md",
      "fallback-reliability.md",
      "memory-template.md",
      "routing-playbooks.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "open-router",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T20:56:49.978Z",
      "expiresAt": "2026-05-09T20:56:49.978Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=open-router",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=open-router",
        "contentDisposition": "attachment; filename=\"open-router-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "open-router"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/open-router"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "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/open-router",
    "downloadUrl": "https://openagent3.xyz/downloads/open-router",
    "agentUrl": "https://openagent3.xyz/skills/open-router/agent",
    "manifestUrl": "https://openagent3.xyz/skills/open-router/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/open-router/agent.md"
  }
}
```
## Documentation

### Setup

On first use, read setup.md to align activation boundaries, reliability goals, and routing preferences before making configuration changes.

### When to Use

Use this skill when the user wants to connect an OpenAI-compatible workflow to OpenRouter, choose models by task type, set safe fallbacks, and control cost drift over time.

### Architecture

Memory lives in ~/open-router/. See memory-template.md for structure.

~/open-router/
├── memory.md            # Active routing profile and constraints
├── providers.md         # Confirmed provider and auth choices
├── routing-rules.md     # Task -> model and fallback policy
├── incidents.md         # Outages, rate limits, and recovery notes
└── budgets.md           # Spend guardrails and optimization actions

### Quick Reference

Use the smallest relevant file for the current task.

TopicFileSetup and activation preferencessetup.mdMemory templatememory-template.mdAuthentication and provider wiringauth-and-provider.mdRouting patterns by workloadrouting-playbooks.mdReliability and fallback handlingfallback-reliability.mdCost controls and spend reviewscost-guardrails.md

### 1. Start from Workload Classes, Not Model Hype

Classify requests first: coding, analysis, extraction, summarization, or long-context synthesis.
Map each class to a primary model and a fallback before changing any defaults.

### 2. Keep Authentication Explicit and Verifiable

Use OPENROUTER_API_KEY from the local environment, never pasted into logs or chat memory.
Validate auth with a minimal request before applying routing changes.

### 3. Design Fallbacks for Failure Modes, Not Convenience

Separate fallback reasons: rate limit, provider outage, latency spike, or output quality failure.
Keep at least one fallback from a different provider family for resilience.

### 4. Enforce Cost Boundaries Before Throughput Tuning

Set cost ceilings by task class and check expected token burn before broad rollout.
Route low-stakes tasks to cheaper models and reserve premium models for high-impact tasks.

### 5. Change One Layer at a Time

Modify either model selection, fallback policy, or budget limits in a single iteration.
After each change, run a quick verification prompt set and record outcome.

### 6. Record Decisions for Repeatability

Save the final routing policy, rationale, and known tradeoffs in memory.
Reuse proven policies instead of repeatedly rebuilding from scratch.

### Common Traps

Choosing one model for every task -> higher cost and unstable quality under varied workloads.
Using same-family fallback chain only -> cascading failures during provider-specific incidents.
Ignoring token limits for long inputs -> truncated responses and hidden quality loss.
Changing routing and budgets simultaneously -> unclear root cause when quality drops.
Running without verification prompts -> broken routing detected only after user-facing failures.

### External Endpoints

These endpoints are used only to discover model metadata and execute routed inference requests under explicit user task intent.

EndpointData SentPurposehttps://openrouter.ai/api/v1/modelsnone or auth header onlyDiscover current model catalog and metadatahttps://openrouter.ai/api/v1/chat/completionsuser prompt content and selected model idExecute routed inference requests

No other data is sent externally.

### Security & Privacy

Data that leaves your machine:

Prompt text and selected model metadata sent to OpenRouter when inference is requested.

Data that stays local:

Routing notes and preferences under ~/open-router/.
Local environment variable references and verification logs.

This skill does NOT:

Request raw API keys in chat.
Store plaintext secrets in skill memory files.
Modify files outside ~/open-router/ for its own state.

### Trust

By using this skill, prompt content is sent to OpenRouter for model execution.
Only install if you trust this service with your data.

### Related Skills

Install with clawhub install <slug> if user confirms:

api — API request design, payload shaping, and response validation patterns
auth — credential handling and auth troubleshooting workflows
models — model comparison and selection guidance
monitoring — runtime health checks and incident tracking practices

### Feedback

If useful: clawhub star open-router
Stay updated: clawhub sync
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: ivangdavila
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-02T20:56:49.978Z
- Expires at: 2026-05-09T20:56:49.978Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/open-router)
- [Send to Agent page](https://openagent3.xyz/skills/open-router/agent)
- [JSON manifest](https://openagent3.xyz/skills/open-router/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/open-router/agent.md)
- [Download page](https://openagent3.xyz/downloads/open-router)