How do I install the Agent Wal skill?

Run npx skillmds@latest add johnalbertini14-glitch/agent-wal in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Wal safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Wal?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Wal free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Wal?

johnalbertini14-glitch (@johnalbertini14-glitch) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Wal by johnalbertini14-glitch

Name: Agent Wal
Rating: 4.2 (5 reviews)
Author: johnalbertini14-glitch

Agent Wal

Write-Ahead Log protocol for agent state persistence. Prevents losing corrections, decisions, and context during conversation compaction. 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.

File contents

Agent WAL (Write-Ahead Log)

Write important state to disk before responding. Prevents the #1 agent failure mode: losing corrections and context during compaction.

Core Rule

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

When to WAL

Trigger	Action Type	Example
User corrects you	`correction`	"No, use Podman not Docker"
You make a key decision	`decision`	"Using CogVideoX-2B for text-to-video"
Important analysis/conclusion	`analysis`	"WAL/VFM patterns should be core infra not skills"
State change	`state_change`	"GPU server SSH key auth configured"
User says "remember this"	`correction`	Whatever they said

Commands

All commands via scripts/wal.py (relative to this skill directory):

# Write before responding
python3 scripts/wal.py append agent1 correction "Use Podman not Docker for all EvoClaw tooling"
python3 scripts/wal.py append agent1 decision "CogVideoX-5B with multi-GPU via accelerate"
python3 scripts/wal.py append agent1 analysis "Signed constraints prevent genome tampering"

# Working buffer (batch writes during conversation, flush before compaction)
python3 scripts/wal.py buffer-add agent1 decision "Some decision"
python3 scripts/wal.py flush-buffer agent1

# Session start: replay lost context
python3 scripts/wal.py replay agent1

# After applying a replayed entry
python3 scripts/wal.py mark-applied agent1 <entry_id>

# Maintenance
python3 scripts/wal.py status agent1
python3 scripts/wal.py prune agent1 --keep 50

Integration Points

On Session Start

Run replay to get unapplied entries
Read the summary into your context
Mark entries as applied after incorporating them

On User Correction

Run append with action_type correction BEFORE responding
Then respond with the corrected behavior

On Pre-Compaction Flush

Run flush-buffer to persist any buffered entries
Then write to daily memory files as usual

During Conversation

For less critical items, use buffer-add to batch writes. Buffer is flushed to WAL on flush-buffer (called during pre-compaction) or manually.

Storage

WAL files: ~/clawd/memory/wal/<agent_id>.wal.jsonl Buffer files: ~/clawd/memory/wal/<agent_id>.buffer.jsonl

Entries are append-only JSONL. Each entry:

{"id": "abc123", "timestamp": "ISO8601", "agent_id": "agent1", "action_type": "correction", "payload": "Use Podman not Docker", "applied": false}

---name: agent-waldescription: Write-Ahead Log protocol for agent state persistence. Prevents losing corrections, decisions, and context during conversation compaction. 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.---# Agent WAL (Write-Ahead Log)Write important state to disk **before** responding. Prevents the #1 agent failure mode: losing corrections and context during compaction.## Core Rule**Write before you respond.** If something is worth remembering, WAL it first.## When to WAL| Trigger | Action Type | Example ||---------|------------|---------|| User corrects you | `correction` | "No, use Podman not Docker" || You make a key decision | `decision` | "Using CogVideoX-2B for text-to-video" || Important analysis/conclusion | `analysis` | "WAL/VFM patterns should be core infra not skills" || State change | `state_change` | "GPU server SSH key auth configured" || User says "remember this" | `correction` | Whatever they said |## CommandsAll commands via `scripts/wal.py` (relative to this skill directory):```bash# Write before respondingpython3 scripts/wal.py append agent1 correction "Use Podman not Docker for all EvoClaw tooling"python3 scripts/wal.py append agent1 decision "CogVideoX-5B with multi-GPU via accelerate"python3 scripts/wal.py append agent1 analysis "Signed constraints prevent genome tampering"# Working buffer (batch writes during conversation, flush before compaction)python3 scripts/wal.py buffer-add agent1 decision "Some decision"python3 scripts/wal.py flush-buffer agent1# Session start: replay lost contextpython3 scripts/wal.py replay agent1# After applying a replayed entrypython3 scripts/wal.py mark-applied agent1 <entry_id># Maintenancepython3 scripts/wal.py status agent1python3 scripts/wal.py prune agent1 --keep 50```## Integration Points### On Session Start1. Run `replay` to get unapplied entries2. Read the summary into your context3. Mark entries as applied after incorporating them### On User Correction1. Run `append` with action_type `correction` BEFORE responding2. Then respond with the corrected behavior### On Pre-Compaction Flush1. Run `flush-buffer` to persist any buffered entries2. Then write to daily memory files as usual### During ConversationFor less critical items, use `buffer-add` to batch writes. Buffer is flushed to WAL on `flush-buffer` (called during pre-compaction) or manually.## StorageWAL files: `~/clawd/memory/wal/<agent_id>.wal.jsonl`Buffer files: `~/clawd/memory/wal/<agent_id>.buffer.jsonl`Entries are append-only JSONL. Each entry:```json{"id": "abc123", "timestamp": "ISO8601", "agent_id": "agent1", "action_type": "correction", "payload": "Use Podman not Docker", "applied": false}```

Frequently asked questions