From agentops
Sweeps .agents directories across workspace rigs, extracts learnings and patterns, deduplicates by content hash, and promotes high-value items to ~/.agents/learnings/. Use before evolve cycles, after multi-rig development, or weekly.
npx claudepluginhub boshu2/agentops --plugin agentopsThis skill uses the workspace's default tool permissions.
> **Nightly usage (2026-04-09):** `/dream start` now runs harvest as part
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Nightly usage (2026-04-09):
/dream startnow runs harvest as part of its bounded compounding loop. Use/harvestfor manual sweeps, CI runs, or when Dream is disabled. Dream holds.agents/overnight/run.lockwhile running — manualao harvestwill refuse until the lock releases.
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.
$harvestpromotes into~/.agents/learnings/, not~/.agents/. Users often say "harvest all to~/.agents" and mean the promotion hub. If you really want every raw artifact (not just the promotion set) mirrored verbatim, you wantrsync, not$harvest.
See docs/skills-decision-tree.md for the full "which skill next?" decision table covering harvest, compile, dream, knowledge-activation, and quickstart.
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/
ao harvest --dry-run --quiet
Read .agents/harvest/latest.json and report:
Skip if --auto is set. Otherwise, show the dry-run summary and ask:
Harvest will promote N artifacts from M rigs to ~/.agents/learnings/.
Proceed? [Approve / Adjust threshold / Abort]
ao harvest --roots ~/gt/ --promote-to ~/.agents/learnings --min-confidence 0.5
Run dedup on the promotion target to clean up any remaining duplicates:
ao dedup --merge ~/.agents/learnings/ 2>/dev/null || true
Report to user:
| Flag | Default | Description |
|---|---|---|
--auto | off | Skip confirmation gate |
--roots | ~/gt/ | Override root directories to scan |
--min-confidence | 0.5 | Minimum confidence for promotion |
--include | learnings,patterns,research | Artifact types to extract |
/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
See references/governance.md for ongoing governance model: size budgets, sweep frequency, staleness thresholds, and cross-rig synthesis triggers.