agent-self-governance
بواسطة bowen31337
DevOps & Cloudموجز
Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL.
الوصف
ما الذي تفعله هذه المهارة
Five protocols that address common agent failure modes: WAL persists context before LLM compaction, VBR prevents false task-complete claims, ADL tracks persona drift, VFM monitors token cost against task value, and IKL captures infrastructure facts before they leave context. Each protocol has its own Python script, defined triggers, and log format.
Rather than relying on agent memory or ad-hoc notes, each failure mode gets a dedicated scriptable protocol with explicit triggers, commands, and log formats that survive context resets.
متى تستخدمها
- Recovering key decisions after LLM context compaction mid-session
- Catching false task-complete claims before they reach the user
- Routing monitoring tasks to budget models instead of burning Opus tokens on simple summarization
- Logging GPU server specs discovered during SSH setup before they drop out of context
- Detecting sycophantic drift in agent responses over long sessions
مثال على سير العمل
User says: 'No, use Podman not Docker'
- 1
Run
python3 scripts/wal.py append <agent_id> correction 'Use Podman not Docker'before responding - 2
Acknowledge the correction to the user
- 3
Update affected configuration or commands to reference Podman
- 4
Run
python3 scripts/vbr.py check task123 command 'podman ps'to verify Podman is available - 5
Log the result with
python3 scripts/vbr.py log <agent_id> task123 true 'Podman confirmed available'
Correction is persisted to WAL before the agent responds, and tooling availability is verified before proceeding
التثبيت
clawhub install bowen31337/agent-self-governanceشغّل أمر واجهة سطر الأوامر، أو الصق النص في Claude Code أو Cursor أو Codex أو أي وكيل برمجة تستخدمه.