arbiterPush decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding.
Install via ClawdBot CLI:
clawdbot install 5hanth/arbiterPush decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding.
Quick install via ClawHub:
clawhub install arbiter
Or via bun (makes CLI commands available globally):
bun add -g arbiter-skill
Or manual:
git clone https://github.com/5hanth/arbiter-skill.git
cd arbiter-skill && npm install && npm run build
ln -s $(pwd) ~/.clawdbot/skills/arbiter
bunx arbiter-zebu)~/.arbiter/queue/ directory (created automatically by the bot)Set these in your agent's environment for automatic agent/session detection:
| Variable | Description | Example |
|----------|-------------|---------|
| CLAWDBOT_AGENT | Agent ID | ceo, swe1 |
| CLAWDBOT_SESSION | Session key | agent:ceo:main |
Do NOT use for:
Create a decision plan for human review.
CLI: arbiter-push ' — takes a single JSON argument containing all fields.
arbiter-push '{
"title": "API Design Decisions",
"tag": "nft-marketplace",
"context": "SWE2 needs these decided before API work",
"priority": "normal",
"notify": "agent:swe2:main",
"decisions": [
{
"id": "auth-strategy",
"title": "Auth Strategy",
"context": "How to authenticate admin users",
"options": [
{"key": "jwt", "label": "JWT tokens", "note": "Stateless"},
{"key": "session", "label": "Sessions", "note": "More control"},
{"key": "oauth", "label": "OAuth", "note": "External provider"}
]
},
{
"id": "database",
"title": "Database Choice",
"context": "Primary datastore",
"options": [
{"key": "postgresql", "label": "PostgreSQL + JSONB"},
{"key": "mongodb", "label": "MongoDB"}
],
"allowCustom": true
}
]
}'
JSON Fields:
| Field | Required | Description |
|-------|----------|-------------|
| title | Yes | Plan title |
| tag | No | Tag for filtering (e.g., project name) |
| context | No | Background for reviewer |
| priority | No | low, normal, high, urgent (default: normal) |
| notify | No | Session to notify when complete |
| agent | No | Agent ID (auto-detected from CLAWDBOT_AGENT env) |
| session | No | Session key (auto-detected from CLAWDBOT_SESSION env) |
| decisions | Yes | Array of decisions |
Decision object:
| Field | Required | Description |
|-------|----------|-------------|
| id | Yes | Unique ID within plan |
| title | Yes | Decision title |
| context | No | Explanation for reviewer |
| options | Yes | Array of {key, label, note?} |
| allowCustom | No | Allow free-text answer (default: false) |
| default | No | Suggested option key |
Returns:
{
"planId": "abc123",
"file": "~/.arbiter/queue/pending/ceo-api-design-abc123.md",
"total": 2,
"status": "pending"
}
Check the status of a decision plan.
CLI: arbiter-status or arbiter-status --tag
arbiter-status abc12345
# or
arbiter-status --tag nft-marketplace
Returns:
{
"planId": "abc123",
"title": "API Design Decisions",
"status": "in_progress",
"total": 3,
"answered": 1,
"remaining": 2,
"decisions": {
"auth-strategy": {"status": "answered", "answer": "jwt"},
"database": {"status": "pending", "answer": null},
"caching": {"status": "pending", "answer": null}
}
}
Get answers from a completed plan.
CLI: arbiter-get or arbiter-get --tag
arbiter-get abc12345
# or
arbiter-get --tag nft-marketplace
Returns:
{
"planId": "abc123",
"status": "completed",
"completedAt": "2026-01-30T01:45:00Z",
"answers": {
"auth-strategy": "jwt",
"database": "postgresql",
"caching": "redis"
}
}
Error if not complete:
{
"error": "Plan not complete",
"status": "in_progress",
"remaining": 2
}
Block until plan is complete (with timeout).
arbiter-await abc12345 --timeout 3600
Polls every 30 seconds until complete or timeout.
Returns: Same as arbiter_get on completion.
# Push plan decisions (single JSON argument)
RESULT=$(arbiter-push '{"title":"Clean IT i18n Plan","tag":"clean-it","priority":"high","notify":"agent:swe3:main","decisions":[{"id":"library","title":"i18n Library","options":[{"key":"i18next","label":"i18next"},{"key":"formatjs","label":"FormatJS"}]},{"id":"keys","title":"Key Structure","options":[{"key":"flat","label":"Flat (login.button)"},{"key":"nested","label":"Nested ({login:{button}})"}]}]}')
PLAN_ID=$(echo $RESULT | jq -r '.planId')
echo "Pushed plan $PLAN_ID — waiting for human review"
# Check if decisions are ready
STATUS=$(arbiter-status --tag nft-marketplace)
if [ "$(echo $STATUS | jq -r '.status')" == "completed" ]; then
ANSWERS=$(arbiter-get --tag nft-marketplace)
AUTH=$(echo $ANSWERS | jq -r '.answers["auth-strategy"]')
echo "Using auth strategy: $AUTH"
# Proceed with implementation
else
echo "Still waiting for $(echo $STATUS | jq -r '.remaining') decisions"
fi
# Wait up to 1 hour for decisions
ANSWERS=$(arbiter-await abc12345 --timeout 3600)
if [ $? -eq 0 ]; then
# Got answers, proceed
echo "Decisions ready: $ANSWERS"
else
echo "Timeout waiting for decisions"
fi
--tag project-name)urgent for true blockers| Path | Purpose |
|------|---------|
| ~/.arbiter/queue/pending/ | Plans awaiting review |
| ~/.arbiter/queue/completed/ | Answered plans (archive) |
| ~/.arbiter/queue/notify/ | Agent notifications |
In your HEARTBEAT.md, add:
## Check Arbiter Notifications
1. Check if `~/.arbiter/queue/notify/` has files for my session
2. If yes, read answers and proceed with blocked work
3. Delete notification file after processing
| Issue | Solution |
|-------|----------|
| Plan not showing in Arbiter | Check file is valid YAML frontmatter |
| Answers not appearing | Check arbiter_status, may be incomplete |
| Notification not received | Ensure --notify was set correctly |
Generated Mar 1, 2026
A development team uses the Arbiter skill to push architectural decisions, such as choosing between microservices or monolith, for async human review by a lead architect. This ensures alignment with company standards before implementation begins, reducing rework.
A marketing team submits campaign plans, including budget allocations and channel strategies, for review by a manager. The Arbiter skill facilitates batch decision-making on multiple aspects, streamlining approvals without blocking team progress.
A product manager pushes decisions on feature prioritization and user story sequencing to stakeholders for review. This allows async input on trade-offs, ensuring critical features are addressed before development sprints start.
A compliance officer uses the skill to review regulatory decisions, such as data handling policies or security protocols, with legal experts. It enables documented async approvals, reducing delays in high-stakes environments.
A research team submits decisions on experimental methodologies or resource allocation for peer review. The Arbiter skill helps gather input from senior scientists asynchronously, maintaining project momentum.
Offer the Arbiter skill as a paid add-on within a larger SaaS platform for project management or DevOps tools. Revenue comes from subscription tiers based on usage volume, such as number of decisions pushed per month.
Provide consulting services to help organizations integrate the Arbiter skill into their workflows, including custom training and support. Revenue is generated through hourly rates or fixed project fees for implementation.
License the Arbiter skill to large enterprises for internal use, with features like advanced analytics and priority support. Revenue comes from annual licensing fees tailored to company size and decision throughput.
💬 Integration Tip
Set up environment variables like CLAWDBOT_AGENT for automatic agent detection, and ensure the Arbiter Zebu bot is running to handle queue processing seamlessly.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Advanced desktop automation with mouse, keyboard, and screen control
Manage n8n workflows and automations via API. Use when working with n8n workflows, executions, or automation tasks - listing workflows, activating/deactivating, checking execution status, manually triggering workflows, or debugging automation issues.
Design and implement automation workflows to save time and scale operations as a solopreneur. Use when identifying repetitive tasks to automate, building workflows across tools, setting up triggers and actions, or optimizing existing automations. Covers automation opportunity identification, workflow design, tool selection (Zapier, Make, n8n), testing, and maintenance. Trigger on "automate", "automation", "workflow automation", "save time", "reduce manual work", "automate my business", "no-code automation".
Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows.