Agent Self-Governance

Five protocols that prevent agent failure modes: losing context, false completion claims, persona drift, wasteful spending, and infrastructure amnesia.

1. WAL (Write-Ahead Log)

Rule: Write before you respond. If something is worth remembering, WAL it first.

Trigger	Action Type	Example
User corrects you	INLINECODE0	"No, use Podman not Docker"
Key decision

decision | "Using CogVideoX-2B for text-to-video" |
| Important analysis | analysis | "WAL patterns should be core infra not skills" |
| State change | state_change | "GPU server SSH key auth configured" |

CODEBLOCK0

Integration Points

• - Session start → replay to recover lost context
• User correction → append BEFORE responding
• Pre-compaction flush → flush-buffer then write daily memory
• During conversation → buffer-add for less critical items

2. VBR (Verify Before Reporting)

Rule: Don't say "done" until verified. Run a check before claiming completion.

CODEBLOCK1

When to VBR

• - After code changes → INLINECODE8
• After file creation → INLINECODE9
• After git push → INLINECODE10
• After sub-agent task → verify the claimed output exists

3. ADL (Anti-Divergence Limit)

Rule: Stay true to your persona. Track behavioral drift from SOUL.md.

CODEBLOCK2

Anti-Patterns Tracked

• - Sycophancy — "Great question!", "I'd be happy to help!"
• Passivity — "Would you like me to", "Shall I", "Let me know if"
• Hedging — "I think maybe", "It might be possible"
• Verbosity — Response length exceeding expected bounds

Persona Signals (Positive)

• - Direct — "Done", "Fixed", "Ship", "Built"
• Opinionated — "I'd argue", "Better to", "The right call"
• Action-oriented — "Spawning", "On it", "Kicking off"

4. VFM (Value-For-Money)

Rule: Track cost vs value. Don't burn premium tokens on budget tasks.

CODEBLOCK3

Task → Tier Guidelines

Task Type	Recommended Tier	Models
Monitoring, formatting, summarization	Budget	GLM, DeepSeek, Haiku
Code generation, debugging, creative

Standard | Sonnet, Gemini Pro |

| Architecture, complex analysis | Premium | Opus, Sonnet+thinking |

When to Check VFM

• - After spawning sub-agents → log cost and outcome
• During heartbeat → run suggest for optimization tips
• Weekly review → run report for cost breakdown

5. IKL (Infrastructure Knowledge Logging)

Rule: Log infrastructure facts immediately. When you discover hardware specs, service configs, or network topology, write it down BEFORE continuing.

Triggers

Discovery Type	Log To	Example
Hardware specs	TOOLS.md	"GPU server has 3 GPUs: RTX 3090 + 3080 + 2070 SUPER"
Service configs

TOOLS.md | "ComfyUI runs on port 8188, uses /data/ai-stack" |

| Network topology | TOOLS.md | "Pi at 192.168.99.25, GPU server at 10.0.0.44" | | Credentials/auth | memory/encrypted/ | "SSH key: ~/.ssh/ided25519alexchen" | | API endpoints | TOOLS.md or skill | "Moltbook API: POST /api/v1/posts" |

Commands to Run on Discovery

CODEBLOCK4

The IKL Protocol

1. 1. SSH to new server → Run hardware/service discovery commands
2. Before responding → Update TOOLS.md with specs
3. New service discovered → Log port, path, config location
4. Credentials obtained → Encrypt and store in memory/encrypted/

Anti-Pattern: "I'll Remember"

❌ "The GPU server has 3 GPUs" (only in conversation) ✅ "The GPU server has 3 GPUs" → Update TOOLS.md → then continue

Memory is limited. Files are permanent. IKL before you forget.