skills$openclaw/arbiter
5hanth883

by 5hanth

arbiter – OpenClaw Skill

arbiter is an OpenClaw Skills integration for data analytics workflows. Push decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding.

883 stars2.2k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026data analytics

Skill Snapshot

namearbiter
descriptionPush decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding. OpenClaw Skills integration.
owner5hanth
repository5hanth/arbiter
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @5hanth/arbiter
last updatedFeb 7, 2026

Maintainer

5hanth

5hanth

Maintains arbiter in the OpenClaw Skills directory.

View GitHub profile
File Explorer
17 files
.
scripts
get.sh
339 B
push.sh
372 B
status.sh
343 B
src
get.ts
2.3 KB
push.ts
4.1 KB
status.ts
2.4 KB
types.ts
1.5 KB
utils.ts
3.3 KB
templates
decision.md
1.5 KB
_meta.json
266 B
package.json
765 B
README.md
3.1 KB
SKILL.md
7.4 KB
tsconfig.json
430 B
SKILL.md

name: arbiter description: Push decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding. metadata: {"openclaw":{"requires":{"bins":["arbiter-push"]}}}

Arbiter Skill

Push decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding.

Installation

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

Prerequisites

  • Arbiter Zebu bot running (or just bunx arbiter-zebu)
  • ~/.arbiter/queue/ directory (created automatically by the bot)

Environment Variables

Set these in your agent's environment for automatic agent/session detection:

VariableDescriptionExample
CLAWDBOT_AGENTAgent IDceo, swe1
CLAWDBOT_SESSIONSession keyagent:ceo:main

When to Use

  • Plan review before implementation
  • Architectural decisions with tradeoffs
  • Anything blocking that needs human judgment
  • Multiple related decisions as a batch

Do NOT use for:

  • Simple yes/no that doesn't need explanation
  • Urgent real-time decisions (use direct message instead)
  • Technical questions you can research yourself

Tools

arbiter_push

Create a decision plan for human review.

CLI: arbiter-push '<json>' — 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:

FieldRequiredDescription
titleYesPlan title
tagNoTag for filtering (e.g., project name)
contextNoBackground for reviewer
priorityNolow, normal, high, urgent (default: normal)
notifyNoSession to notify when complete
agentNoAgent ID (auto-detected from CLAWDBOT_AGENT env)
sessionNoSession key (auto-detected from CLAWDBOT_SESSION env)
decisionsYesArray of decisions

Decision object:

FieldRequiredDescription
idYesUnique ID within plan
titleYesDecision title
contextNoExplanation for reviewer
optionsYesArray of {key, label, note?}
allowCustomNoAllow free-text answer (default: false)
defaultNoSuggested option key

Returns:

{
  "planId": "abc123",
  "file": "~/.arbiter/queue/pending/ceo-api-design-abc123.md",
  "total": 2,
  "status": "pending"
}

arbiter_status

Check the status of a decision plan.

CLI: arbiter-status <plan-id> or arbiter-status --tag <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}
  }
}

arbiter_get

Get answers from a completed plan.

CLI: arbiter-get <plan-id> or arbiter-get --tag <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
}

arbiter_await

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.

Usage Examples

Example 1: Plan Review

# 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"

Example 2: Check and Proceed

# 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

Example 3: Blocking Wait

# 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

Best Practices

  1. Batch related decisions — Don't push one at a time
  2. Provide context — Human needs to understand tradeoffs
  3. Use tags — Makes filtering easy (--tag project-name)
  4. Set notify — So blocked agents get woken up
  5. Use priority sparingly — Reserve urgent for true blockers

File Locations

PathPurpose
~/.arbiter/queue/pending/Plans awaiting review
~/.arbiter/queue/completed/Answered plans (archive)
~/.arbiter/queue/notify/Agent notifications

Checking Notifications (Agent Heartbeat)

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

Troubleshooting

IssueSolution
Plan not showing in ArbiterCheck file is valid YAML frontmatter
Answers not appearingCheck arbiter_status, may be incomplete
Notification not receivedEnsure --notify was set correctly

See Also

README.md

Arbiter Skill

Agent-side CLI for pushing decisions to Arbiter Zebu. Works with Clawdbot/OpenClaw agents or standalone.

Install

Via ClawHub (for Clawdbot/OpenClaw):

clawhub install arbiter

Via npm/bun (standalone CLI):

bun add -g arbiter-skill

Prerequisites

  • Arbiter Zebu bot running (bunx arbiter-zebu)
  • ~/.arbiter/queue/ directory (created automatically by the bot)

CLI Commands

arbiter-push

Push a decision plan for human review:

arbiter-push '{
  "title": "API Design Decisions",
  "tag": "my-project",
  "priority": "high",
  "notify": "agent:swe1:main",
  "decisions": [
    {
      "id": "auth",
      "title": "Auth Method",
      "context": "How to authenticate users",
      "options": [
        {"key": "jwt", "label": "JWT tokens"},
        {"key": "session", "label": "Server sessions"},
        {"key": "oauth", "label": "OAuth provider"}
      ]
    },
    {
      "id": "database",
      "title": "Database Choice",
      "context": "Primary datastore",
      "options": [
        {"key": "pg", "label": "PostgreSQL"},
        {"key": "mongo", "label": "MongoDB"}
      ]
    }
  ]
}'

Returns:

{
  "planId": "abc123",
  "file": "~/.arbiter/queue/pending/ceo-api-design-abc123.md",
  "total": 2,
  "status": "pending"
}

arbiter-status

Check plan status:

arbiter-status '{"planId": "abc123"}'
# or by tag
arbiter-status '{"tag": "my-project"}'

arbiter-get

Get answers from a completed plan:

arbiter-get '{"planId": "abc123"}'

Returns:

{
  "planId": "abc123",
  "status": "completed",
  "answers": {
    "auth": "jwt",
    "database": "pg"
  }
}

How It Works

arbiter-push writes markdown → ~/.arbiter/queue/pending/
                                      ↓
                    Arbiter Zebu bot detects new file
                                      ↓
                    Human reviews & answers in Telegram
                                      ↓
                    On completion, notification written to
                    ~/.arbiter/queue/notify/
                                      ↓
                    Agent picks up answers (heartbeat or poll)

JSON Fields

Push args

FieldRequiredDescription
titleYesPlan title
tagNoProject tag for filtering
contextNoBackground for the reviewer
priorityNolow / normal / high / urgent
notifyNoSession key to notify on completion
decisionsYesArray of decision objects

Decision object

FieldRequiredDescription
idYesUnique ID within the plan
titleYesHuman-readable title
contextNoExplanation for the reviewer
optionsYesArray of {key, label}
allowCustomNoAllow free-text answers

Usage with Clawdbot

See SKILL.md for full agent integration docs.

License

MIT

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

- [Arbiter Zebu](https://github.com/5hanth/arbiter-zebu) bot running (or just `bunx arbiter-zebu`) - `~/.arbiter/queue/` directory (created automatically by the bot)

FAQ

How do I install arbiter?

Run openclaw add @5hanth/arbiter in your terminal. This installs arbiter into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/5hanth/arbiter. Review commits and README documentation before installing.