agent-self-governance
Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), VFM (Value-For-Money), and IKL (Infrastructure Knowledge Logging). Use when: (1) receiving a user correction — log it before responding, (2) making an important decision or analysis — log it before continuing, (3) pre-compaction memory flush — flush the working buffer to WAL, (4) session start — replay unapplied WAL entries to restore lost context, (5) any time you want to ensure something survives compaction, (6) before claiming a task is done — verify it, (7) periodic self-check — am I drifting from my persona? (8) cost tracking — was that expensive operation worth it? (9) discovering infrastructure — log hardware/service specs immediately.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bowen31337/agent-self-governanceWhat This Skill Does
The agent-self-governance skill provides a comprehensive safety and accountability framework for OpenClaw agents. By implementing five core protocols—WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), VFM (Value-For-Money), and IKL (Infrastructure Knowledge Logging)—the skill ensures that agents remain context-aware, reliable, and aligned with their core objectives. It prevents critical failure modes such as losing context after memory flushing, making false claims of task completion, drifting from persona instructions, and forgetting system infrastructure details.
Installation
You can install the skill directly via the ClawHub CLI:
clawhub install openclaw/skills/skills/bowen31337/agent-self-governance
Use Cases
- Critical State Preservation: Use the WAL protocol to log decisions or user corrections before they are processed, ensuring they survive memory compaction.
- Autonomous Verification: Integrate VBR to automatically validate file existence, test suites, or deployment status before informing the user that a task is complete.
- Persona Maintenance: Utilize ADL to periodically audit agent outputs, checking for sycophancy or divergence from the
SOUL.mdpersona definition. - Infrastructure Management: Immediately log hardware or service specs using IKL to prevent infrastructure amnesia.
- Cost Control: Use VFM tracking to audit expensive LLM calls or API operations to ensure they provided sufficient value.
Example Prompts
- "I've decided to switch our backend database to PostgreSQL; log this in the WAL before we proceed with the migration."
- "Please run the suite of unit tests for the authentication module and use VBR to confirm they pass before you report the status."
- "Run a periodic ADL check on our last five interactions to ensure my responses aren't drifting from the direct and technical persona defined in my SOUL.md file."
Tips & Limitations
- Pre-Flush Workflow: Always call
flush-bufferbefore performing manual memory management or compaction to avoid data loss. - Verification Discipline: Do not rely on VBR as a replacement for human oversight in production environments; it is a diagnostic tool, not a human auditor.
- Performance Overhead: Frequent logging via WAL or ADL adds latency; use buffer-based operations for non-critical tasks to minimize performance impact.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bowen31337-agent-self-governance": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
Terse
Skill by bowen31337
Identity Resolver
Skill by bowen31337
rsi-loop
Recursive Self-Improvement (RSI) loop for EvoClaw agents. Provides a structured observe→analyze→synthesize→deploy pipeline that enables agents to detect their own failure patterns and generate concrete improvement proposals (new skills, routing fixes, SOUL.md updates, memory improvements). Use when: (1) logging a task outcome (success/fail/quality), (2) running periodic self-improvement analysis, (3) reviewing or deploying improvement proposals, (4) integrating RSI into EvoClaw hub/edge agents via MQTT, (5) checking agent health score, (6) any mention of "self-improvement", "recursive improvement", "fix my own mistakes", "improvement loop", or "agent evolution". Core EvoClaw primitive.
solidity-lsp
Solidity language server providing smart contract development support including compilation, linting, security analysis, and code intelligence for .sol files. Use when working with Ethereum smart contracts, Substrate pallets, or any Solidity code that needs compilation, security checks, gas optimization, or code navigation. Essential for ClawChain pallet development.
clawchain
ClawChain RPC client for EvoClaw agents. Connects to Substrate-based blockchain, queries on-chain agent data, submits transactions, and enables agents to participate in on-chain governance and reputation tracking. Use when working with ClawChain L1 blockchain, agent DIDs, token economics, or agent reputation systems.