# Send Agent Hive 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": "agent-hive", "name": "Agent Hive", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/nissan/agent-hive", "canonicalUrl": "https://clawhub.ai/nissan/agent-hive", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/agent-hive", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-hive", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/governance.md", "references/heartbeat-snippet.md", "scripts/budget_audit.py", "scripts/create_agent.sh" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "agent-hive", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T01:45:42.143Z", "expiresAt": "2026-05-06T01:45:42.143Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-hive", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-hive", "contentDisposition": "attachment; filename=\"agent-hive-1.0.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agent-hive" }, "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/agent-hive" }, "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/agent-hive", "downloadUrl": "https://openagent3.xyz/downloads/agent-hive", "agentUrl": "https://openagent3.xyz/skills/agent-hive/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-hive/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-hive/agent.md" } } ``` ## Documentation ### Agent Hive Create and manage multi-agent teams with shared memory, budget governance, and configurable spawn permissions. ### Architecture Main Workspace (~/.openclaw/workspace/) ├── MEMORY.md, TOOLS.md, USER.md, IDENTITY.md ← shared brain (real files) ├── agents// ← per-agent outbox, inbox, budget ├── agents/governance/ ← governance rules + audit log ├── memory/, projects/, scripts/, skills/ ← shared resources └── content/ ← shared content Agent Workspace (~/.openclaw/workspace-/) ├── SOUL.md ← unique personality (local file) ├── AGENTS.md ← unique instructions (local file) ├── HEARTBEAT.md ← agent-specific heartbeat (local file) ├── .openclaw/ ← agent-specific config dir └── everything else ← SYMLINKS to main workspace ### Step 1: Create workspace with symlinks AGENT_ID="" MAIN="$HOME/.openclaw/workspace" WS="$HOME/.openclaw/workspace-$AGENT_ID" mkdir -p "$WS/.openclaw" # Symlink shared brain for f in .learnings IDENTITY.md MEMORY.md ROADMAP.md TOOLS.md USER.md; do ln -sf "../workspace/$f" "$WS/$f" done for d in agents content memory projects scripts skills; do ln -sf "../workspace/$d" "$WS/$d" done ### Step 2: Create unique files Create $WS/SOUL.md — the agent's personality. This is theirs alone. Create $WS/AGENTS.md — agent-specific instructions. Must include: Session startup checklist (read SOUL.md, check BUDGET.json, check INBOX.md) Communication rules (INBOX/OUTBOX pattern) What the agent does and doesn't do Budget rules section (see references/budget-rules.md) Create $WS/HEARTBEAT.md — minimal heartbeat config. ### Step 3: Create agent directory in shared workspace mkdir -p "$MAIN/agents/$AGENT_ID" touch "$MAIN/agents/$AGENT_ID/INBOX.md" touch "$MAIN/agents/$AGENT_ID/OUTBOX.md" ### Step 4: Create budget file Copy scripts/create_budget.sh output or create manually: { "daily_limit_output_tokens": 50000, "today": "YYYY-MM-DD", "used_output_tokens": 0, "spawns": [], "status": "active", "warnings": [], "consecutive_overbudget_days": 0 } Save to $MAIN/agents/$AGENT_ID/BUDGET.json. ### Step 5: Register in openclaw.json Add to agents.list[]: { "id": "", "name": "", "workspace": "/absolute/path/to/workspace-", "identity": { "name": "", "emoji": "" }, "model": { "primary": "anthropic/claude-sonnet-4-6", "fallbacks": ["", ""] }, "subagents": { "allowAgents": ["", ""] } } Update existing agents' allowAgents to include the new agent. ### Step 6: Validate and restart python3 -c "import json; json.load(open('$HOME/.openclaw/openclaw.json')); print('JSON valid')" openclaw doctor # check for schema errors launchctl stop ai.openclaw.gateway && sleep 2 && launchctl start ai.openclaw.gateway Wait 15 seconds before testing. ### Hub-and-spoke (conservative) Only the orchestrator (main) can spawn agents. Agents route requests through OUTBOX. "subagents": { "allowAgents": [] } // for all non-main agents ### Full mesh with budget (recommended) All agents can spawn peers. Budget governance prevents abuse. // Each agent can spawn all peers (not themselves) "subagents": { "allowAgents": [""] } ### Earned mesh (progressive trust) Start hub-and-spoke. Promote to mesh after demonstrating budget responsibility. Demote back to hub-and-spoke after repeated overspend. ### Budget Governance See references/governance.md for the full framework. Run the audit script on heartbeat: python3 scripts/budget_audit.py Thresholds: Green (<80%), Yellow (80-100%), Red (>100%), Emergency demotion (>200%). 3 consecutive overbudget days → automatic demotion (mesh privileges revoked). Add step 4.5 to your HEARTBEAT.md — see references/heartbeat-snippet.md. ### Committee Pattern For project work, compose agent committees: Identify which agents are needed (e.g., content + marketing + design review) Spawn them in parallel with clear, scoped tasks Each writes to their OUTBOX.md Orchestrator collects results and synthesizes Budget tracked per-agent across the project ### Verification Checklist After adding an agent, verify: workspace-/ has SOUL.md + AGENTS.md as local files All other files are symlinks to main workspace agents//BUDGET.json exists with correct schema Agent appears in openclaw doctor output Gateway restarts without errors Agent can be spawned: sessions_spawn(agentId="", task="Say hello") Budget audit includes the new agent: python3 scripts/budget_audit.py ## Trust - Source: tencent - Verification: Indexed source record - Publisher: nissan - Version: 1.0.1 ## 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: 2026-04-29T01:45:42.143Z - Expires at: 2026-05-06T01:45:42.143Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/agent-hive) - [Send to Agent page](https://openagent3.xyz/skills/agent-hive/agent) - [JSON manifest](https://openagent3.xyz/skills/agent-hive/agent.json) - [Markdown brief](https://openagent3.xyz/skills/agent-hive/agent.md) - [Download page](https://openagent3.xyz/downloads/agent-hive)