Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Agent Swarm
IMPORTANT: OpenRouter is required. Routes tasks to the right model and always delegates work through sessions_spawn.
skill openclawclawhub Free
IMPORTANT: OpenRouter is required. Routes tasks to the right model and always delegates work through sessions_spawn.
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- README.md, REVIEW-name-conformity.md, SKILL.md, _meta.json, config.json, scripts/router.py
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- 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.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.7.19
Provenance
- Publisher
- RuneweaverStudios
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Description
IMPORTANT: OpenRouter is required. Routes tasks to the right model and always delegates work through sessions_spawn.
Before installing
OPENCLAW_HOME: Not required. The skill uses OPENCLAW_HOME only if set; otherwise it defaults to ~/.openclaw. This is consistent in both metadata (_meta.json: listed in optionalEnv, not in env) and behavior. openclaw.json read access: The skill reads the local file openclaw.json (at $OPENCLAW_HOME/openclaw.json or ~/.openclaw/openclaw.json). Only the fields tools.exec.host and tools.exec.node are used; no gateway secrets or API keys are read. Verify you are comfortable granting read access to that file before installing.
Single task
Router output: {"task":"write a poem","model":"openrouter/moonshotai/kimi-k2.5","sessionTarget":"isolated"} Then call: sessions_spawn(task="write a poem", model="openrouter/moonshotai/kimi-k2.5", sessionTarget="isolated")
Parallel tasks
python3 workspace/skills/agent-swarm/scripts/router.py spawn --json --multi "fix bug and write poem" This returns multiple spawn configs. Start one sub-agent per config.
Commands
Manual/CLI use only. The examples below pass the task as a single argument; for programmatic use with untrusted user input, always invoke the router via subprocess.run(..., [..., user_message], ...) with a list of arguments (see Security). Do not build a shell command string from user input. python scripts/router.py default python scripts/router.py classify "fix lint errors" python scripts/router.py spawn --json "write a poem" python scripts/router.py spawn --json --multi "fix bug and write poem" python scripts/router.py models
What this skill does
Agent Swarm is a traffic cop for AI models. It picks the best model for each task, then starts a sub-agent to do the work.
IMPORTANT: OpenRouter is required
Required Platform Configuration: OpenRouter API key: Must be configured in OpenClaw platform settings (not provided by this skill) OPENCLAW_HOME (optional): Environment variable pointing to OpenClaw workspace root. If not set, defaults to ~/.openclaw openclaw.json access: The router reads tools.exec.host and tools.exec.node from openclaw.json (located at $OPENCLAW_HOME/openclaw.json or ~/.openclaw/openclaw.json). Only these two fields are accessed; no gateway secrets or API keys are read. Model Requirements: Model IDs must use openrouter/... prefix If OpenRouter is not configured in OpenClaw, delegation will fail
Why this helps
Faster replies (cheap orchestrator, smart sub-agent routing) Better quality (code tasks go to code models, writing tasks go to writing models) Lower cost (you do not run every task on the most expensive model)
Core rule (non-negotiable)
For user tasks, the orchestrator must delegate. It must NOT answer the task itself. Use this flow every time: Run router. From orchestrator code, use subprocess with a list of arguments (never shell interpolation with user input): import subprocess result = subprocess.run( ["python3", "/path/to/workspace/skills/agent-swarm/scripts/router.py", "spawn", "--json", user_message], capture_output=True, text=True ) data = json.loads(result.stdout) if result.returncode == 0 else {} CLI only (manual testing; do not use from code with untrusted user input): python3 workspace/skills/agent-swarm/scripts/router.py spawn --json "your task here" Use OPENCLAW_HOME or absolute path for the script when not in workspace root. If needs_config_patch is true: stop and report that patch to the user. Otherwise call: sessions_spawn(task=..., model=..., sessionTarget=...) Wait for sessions_spawn result. Return the sub-agent result to the user. If sessions_spawn fails, return only a delegation failure message. Do not do the task yourself.
Config basics
Edit config.json in the skill root (parent of scripts/) to change routing.
What you can change
WhatKeyPurposeOrchestrator / session defaultdefault_modelMain agent and new sessions (e.g. Gemini 2.5 Flash)Task-specific model per tierrouting_rules.<TIER>.primaryModel used when a task matches that tierBackup models if primary failsrouting_rules.<TIER>.fallbackArray of model IDs to try next
All task-specific tiers (change the model for each)
TierKey to change primaryTypical useFASTrouting_rules.FAST.primarySimple tasks: check, list, status, fetchREASONINGrouting_rules.REASONING.primaryLogic, math, step-by-step analysisCREATIVErouting_rules.CREATIVE.primaryWriting, stories, UI/UX, designRESEARCHrouting_rules.RESEARCH.primaryResearch, search, fact-findingCODErouting_rules.CODE.primaryCode, debug, refactor, implementQUALITYrouting_rules.QUALITY.primaryComplex/architecture tasksCOMPLEXrouting_rules.COMPLEX.primaryMulti-step / complex system tasksVISIONrouting_rules.VISION.primaryImage analysis, screenshots, visual To change all task-specific models: edit each routing_rules.<TIER>.primary above. Use model IDs from the models array in config.json (must start with openrouter/).
Simple config examples
Orchestrator only (keep defaults for tiers): { "default_model": "openrouter/google/gemini-2.5-flash" } (Other keys like routing_rules and models can stay as in the shipped config.json.) Change one tier (e.g. CODE to MiniMax): "routing_rules": { "CODE": { "primary": "openrouter/minimax/minimax-m2.5", "fallback": ["openrouter/qwen/qwen3-coder-flash"] } } Change multiple tiers (primaries only): "routing_rules": { "CREATIVE": { "primary": "openrouter/moonshotai/kimi-k2.5", "fallback": [] }, "CODE": { "primary": "openrouter/z-ai/glm-4.7-flash", "fallback": ["openrouter/minimax/minimax-m2.5"] }, "RESEARCH": { "primary": "openrouter/x-ai/grok-4.1-fast", "fallback": [] } } Only include tiers you want to override; the rest are read from the full config.json.
Input Validation
The router validates and sanitizes all inputs to prevent injection attacks: Task strings: Validated for length (max 10KB), null bytes; rejects prompt-injection patterns (script tags, javascript: protocol, event-handler attributes). Invalid tasks raise ValueError with a clear message. Config patches: Only allows modifications to tools.exec.host and tools.exec.node (whitelist approach) Labels: Validated for length and null bytes
Safe Execution
Critical: When calling router.py from orchestrator code, always use subprocess with a list of arguments, never shell string interpolation: # β SAFE: Use subprocess with list arguments import subprocess result = subprocess.run( ["python3", "/path/to/router.py", "spawn", "--json", user_message], capture_output=True, text=True ) # β UNSAFE: Shell string interpolation (vulnerable to injection) import os os.system(f'python3 router.py spawn --json "{user_message}"') # DON'T DO THIS The router uses Python's argparse, which safely handles arguments when passed as a list. Shell string interpolation is vulnerable to command injection if the user message contains shell metacharacters.
Config Patch Safety
The recommended_config_patch only modifies safe fields: tools.exec.host (must be 'sandbox' or 'node') tools.exec.node (only when host is 'node') All config patches are validated before being returned. The orchestrator should validate patches again before applying them to openclaw.json.
Prompt Injection Mitigation
The router rejects task strings that contain prompt-injection patterns (e.g. <script>, javascript:, onclick=). Rejected tasks raise ValueError; the orchestrator should surface a clear message and not pass the task to sub-agents. Additional layers: The orchestrator (validating task strings and handling rejections) The sub-agent LLM (resisting prompt injection) The OpenClaw platform (sanitizing sessions_spawn inputs)
File Access
Required File Access: Read: openclaw.json (located via OPENCLAW_HOME environment variable or ~/.openclaw/openclaw.json) Fields accessed: tools.exec.host and tools.exec.node only Purpose: Determine execution environment for spawned sub-agents Security: The router does NOT read gateway secrets, API keys, or any other sensitive configuration Write Access: Write: None (no files are written by this skill) Config patches: The skill may return recommended_config_patch JSON that the orchestrator can apply, but the skill itself does not write to openclaw.json Security Guarantees: The router does not persist, upload, or transmit any tokens or credentials Only tools.exec.host and tools.exec.node are accessed from openclaw.json All file access is read-only except for validated config patches (whitelisted to tools.exec.* only)
Other Security Notes
This skill does not expose gateway secrets. Use gateway-guard separately for gateway/auth management. The router does not execute arbitrary code or modify files outside of config patches. The phrase "saves tokens" in documentation refers to cost savings (using cheaper models for simple tasks), not token storage or collection.
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
3 Docs2 Config1 Scripts
- SKILL.md
- README.md
- REVIEW-name-conformity.md
- scripts/router.py
- _meta.json
- config.json