LaunchKit · 2026
Back to Skills

agent-wal

Write-Ahead Log protocol for agent state persistence.

1
827 downloads
by @bowen31337

Setup & Installation

openclaw skills install @bowen31337/agent-wal

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install agent-wal

Version History

v1.0.1Feb 14, 2026 - Version note by skill developer:

Sanitize personal info from examples

What This Skill Does

Write-Ahead Log protocol for persisting agent state to disk before responding. Prevents corrections, decisions, and context from being lost when conversations are compacted. Entries are stored as append-only JSONL and can be replayed at session start to restore lost context.

Unlike relying on in-memory context alone, WAL entries persist to disk and survive compaction, so corrections made early in a session are not silently discarded.

When to use it

  • Preserving a user correction across a session restart
  • Logging an architectural decision before continuing a long conversation
  • Flushing buffered context before anticipated compaction
  • Replaying missed corrections at the start of a new agent session
  • Batching state changes during a complex multi-step task

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User says: 'No, use Podman not Docker for all tooling'

AGENT
  1. 1Runs `wal.py append agent1 correction 'Use Podman not Docker for all tooling'` before responding
  2. 2Confirms entry is written to the JSONL WAL file at ~/clawd/memory/wal/agent1.wal.jsonl
  3. 3Responds to the user with the corrected behavior applied
  4. 4On next session start, runs `wal.py replay agent1` to surface unapplied entries
  5. 5Marks the entry as applied after incorporating it into context
OUTPUT

Correction persisted to disk and restored at the next session start, with no manual re-statement needed from the user