Agentops harvest
git clone https://github.com/boshu2/agentops
T=$(mktemp -d) && git clone --depth=1 https://github.com/boshu2/agentops "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/harvest" ~/.claude/skills/boshu2-agentops-harvest-1c63e6 && rm -rf "$T"
skills/harvest/SKILL.mdHarvest — Cross-Rig Knowledge Consolidation
Nightly usage (2026-04-09):
now runs harvest as part of its bounded compounding loop. Use/dream startfor manual sweeps, CI runs, or when Dream is disabled. Dream holds/harvestwhile running — manual.agents/overnight/run.lockwill refuse until the lock releases.ao harvest
Sweep all
.agents/ directories across the workspace, extract learnings, patterns,
and research, deduplicate cross-rig, and promote high-value items to the global
knowledge hub (~/.agents/learnings/).
Naming gotcha.
promotes into$harvest, not~/.agents/learnings/. Users often say "harvest all to~/.agents/" and mean the promotion hub. If you really want every raw artifact (not just the promotion set) mirrored verbatim, you want~/.agents, notrsync.$harvest
Which skill do I need?
See docs/skills-decision-tree.md for the full "which skill next?" decision table covering harvest, compile, dream, knowledge-activation, and quickstart.
What This Skill Does
The knowledge flywheel captures learnings per-rig, but they stay siloed. Harvest closes the loop by walking all rigs, extracting artifacts, deduplicating by content hash, and promoting high-confidence items to the global hub where every rig can access them via
ao inject.
When to use: Before an evolve cycle, after a burst of development across multiple rigs, or weekly as part of knowledge governance.
Output:
.agents/harvest/latest.json (catalog) + promoted files in ~/.agents/learnings/
Execution Steps
Step 1: Preview Scope (Dry Run)
ao harvest --dry-run --quiet
Read
.agents/harvest/latest.json and report:
- Rigs discovered
- Total artifacts extracted
- Unique vs duplicate count
- Promotion candidates (artifacts >= min confidence)
Step 2: Confirm Execution
Skip if
is set. Otherwise, show the dry-run summary and ask:--auto
Harvest will promote N artifacts from M rigs to ~/.agents/learnings/. Proceed? [Approve / Adjust threshold / Abort]
Step 3: Execute Harvest
ao harvest --roots ~/gt/ --promote-to ~/.agents/learnings --min-confidence 0.5
Step 4: Post-Harvest Cleanup
Run dedup on the promotion target to clean up any remaining duplicates:
ao dedup --merge ~/.agents/learnings/ 2>/dev/null || true
Step 5: Report Results
Report to user:
- Rigs scanned
- Artifacts extracted and unique count
- Duplicates found (with top duplicate groups)
- Artifacts promoted (with provenance)
- Top discoveries (highest-confidence cross-rig patterns)
Flags
| Flag | Default | Description |
|---|---|---|
| off | Skip confirmation gate |
| | Override root directories to scan |
| 0.5 | Minimum confidence for promotion |
| | Artifact types to extract |
Quick Start
/harvest # Full sweep with confirmation /harvest --auto # Hands-free sweep /harvest --min-confidence 0.7 # Only promote high-confidence items /harvest --roots ~/gt/,~/projects/ # Scan additional directories
Governance
See references/governance.md for ongoing governance model: size budgets, sweep frequency, staleness thresholds, and cross-rig synthesis triggers.
See Also
- skills/compile/SKILL.md — Single-rig Mine/Grow/Defrag
- skills/flywheel/SKILL.md — Flywheel health monitoring
- skills/inject/SKILL.md — Knowledge injection into sessions
- skills/forge/SKILL.md — Transcript knowledge extraction
Reference Documents
- references/governance.md — Governance model for ongoing knowledge consolidation