compound-learnings

Compound Learnings

Transform recurring patterns into durable artifacts. Use frequency-based thresholds to distinguish noise from signal.

Data Sources

Scan these locations for patterns:

Note: Session ledger (.agents-os/session_ledger.md) is for /reflect only - ephemeral per-session state.

Pattern Extraction

Step 1: Gather Raw Patterns

# Git patterns (look for repeated prefixes/types)
git log --oneline -100 | cut -d' ' -f2- | sort | uniq -c | sort -rn

# Handoff patterns
grep -h "^- " .agents-os/handoffs/*.md 2>/dev/null | sort | uniq -c | sort -rn

Step 2: Consolidate Similar Patterns

Before counting, normalize patterns:

• "Always validate X" + "Validate X before Y" → "Validate X"
• "Don't use Z" + "Avoid Z" + "Z causes issues" → "Avoid Z"

Group by semantic meaning, not exact wording.

Step 3: Apply Frequency Thresholds

Artifact Categorization

Use this decision tree to determine artifact type:

Is it a sequential workflow with distinct phases?
  YES → Consider COMMAND (user-invoked) or AGENT (autonomous)
    Does it need user interaction during execution?
      YES → COMMAND
      NO → AGENT
  NO ↓

Should it trigger automatically on file/context patterns?
  YES → SKILL (probabilistic, Claude MAY follow)
    Is enforcement critical (must happen every time)?
      YES → Consider HOOK instead (deterministic)
  NO ↓

Is it a simple rule or convention?
  YES → RULE (add to CLAUDE.md or .agents-os/lessons/)
    Project-specific? → .agents-os/lessons/ (with workflow_phase: review)
    Universal? → CLAUDE.md
  NO ↓

Does it enhance an existing agent's behavior?
  YES → AGENT UPDATE (modify existing agent)
  NO → Likely doesn't need encoding

Quick Reference

Output Format

Present findings as:

## Compound Learnings Analysis

### Strong Signal (4+ occurrences)
| Pattern | Count | Recommended Artifact | Rationale |
|---------|-------|---------------------|-----------|
| ... | ... | ... | ... |

### Emerging Patterns (2-3 occurrences)
| Pattern | Count | Potential Artifact | Notes |
|---------|-------|-------------------|-------|
| ... | ... | ... | ... |

### Recommended Actions
1. **[Artifact Type]**: `name` - description
   - Draft: [brief template or content]

Quality Checks

Before recommending an artifact, verify:

• Generality: Applies beyond the specific incidents where it was observed
• Specificity: Concrete enough to act on (not vague advice)
• Uniqueness: Doesn't duplicate existing CLAUDE.md rules or skills
• Correct Type: Matches the categorization decision tree

Integration with /learn

When invoked from /learn:

1. Locate main worktree for centralized handoffs
2. Gather patterns from git, PRs, and handoffs
3. Consolidate and count frequencies
4. Apply thresholds
5. Categorize recommended artifacts
6. Present findings with draft content
7. If approved, create artifacts using appropriate tools

Note: /reflect is for single-session analysis. /learn is for cross-session compound learning.