Drift learn
A drop-in self-improving memory + operations harness for AI agents (OpenClaw / Hermes / Claude Code / Codex). Layered memory, autonomous drift-fixing loop, evals, and one-command DR. Templates + scripts, no secrets.
npx -y skills add Walliiee/agent-harness --skill drift-learnAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Weekly Drift incident learning pass. Reads accumulated incidents, clusters them, and produces compound lessons (Phase 4 of the Drift incident pipeline).
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.5 KB, 314 tokens by cl100k_base, as published. Nobody here has run it
drift-learn — weekly incident clustering pass
Phase 4 of the Drift incident ledger: take a week of ${OPENCLAW_HOME}/incidents/YYYY-MM-DD/*.md records and produce compound lessons (patterns that recur, root causes, recommended skill patches).
When this runs
- Primary: cron.
ai.openclaw.drift-learn.plistfires Sunday 04:30. - Wrapper: through
skill-wrapper --skill drift-learn --agent main --trigger cron.
What it does
Invokes ${OPENCLAW_HOME}/bin/incident-learn --verbose:
- Scan the past 7 days of incident records.
- Cluster by taxonomy (cron-postmortem, memory-capture-bypass, etc.).
- Generate lesson candidates with LLM analysis.
- Append to
${OPENCLAW_HOME}/incidents/lessons/YYYY-WW.md.
Exit codes
0— success or partial successnon-zero— script-level failure
Files
- Script:
${OPENCLAW_HOME}/bin/incident-learn - Plist:
$HOME/Library/LaunchAgents/ai.openclaw.drift-learn.plist - This spec:
${OPENCLAW_HOME}/skills/drift-learn/SKILL.md
Related
drift-watcher— emits incidents this skill consumes.incident-emit,incident-analyze,incident-notify— incident pipeline phases 1-3.
Gives 0 of the 12 instructions most learn study skills give in 314 tokens
Counted across 546 of the 573 authors here whose files we hold, read 2026-08-06
- produce self-contained HTML lessonsin 24 of 546, across 8 files
- record user preferences in a notes filein 23 of 546, across 5 files
- calculate the zone of proximal development before teachingin 23 of 546, across 6 files
- maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
- make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
- create reusable components for lessonsin 19 of 546, across 5 files
- create compressed reference documents for quick lookupin 19 of 546, across 3 files
- find high-quality resources before writing lessonsin 18 of 546, across 4 files
- update the mission file and records upon mission changesin 16 of 546, across 2 files
- set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
- populate the mission file before teachingin 15 of 546, across 1 file
- include interactive feedback loops in lessonsin 15 of 546, across 1 file
Said here and by no other author read
- scan the past 7 days of incident records
- cluster incidents by taxonomy
- generate lesson candidates with llm analysis
- append to the weekly lessons file
- use verbose mode
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.