Harvest

Capture high-signal conversation knowledge into docs/notes/ for reuse across sessions.

When to Trigger

Explicit request:

• “harvest”, “/harvest”
• “harvest this”, “harvest this conversation”
• “save this to second brain”
• “document this work”, “capture this knowledge”

Natural breakpoints — AI may suggest (never auto-execute):

• Significant decision made
• Complex problem solved after multiple attempts
• Important lesson learned
• Discussion wrapping up with valuable content

We just [made a decision/solved X/learned Y].
Would you like me to update the second brain?

Wait for user confirmation. Never auto-execute.

Non-Negotiables

• Never auto-execute. Always wait for explicit user confirmation.
• Use template files as the single source of structure.
• Keep context_id in frontmatter for smart merge.
• Keep MOCs as index files: link to context anchors, do not duplicate full lesson content.
• Omit optional empty sections. Do not write empty headers or “None” placeholders.
• Keep behavior logic in this file; keep structure/manifest data in references/.

Quick Start

1. Ensure docs/notes/ exists (initialize when missing).
2. Run lesson review for this harvest run.
3. Detect context_id and check whether matching context file exists.
4. Create new context or smart-merge existing context.
5. Update docs/notes/00-INDEX.md and related MOCs.
6. Confirm created/updated files to user.

Workflow

Phase 1: Prepare

1. Initialize second brain storage when docs/notes/ is missing:
   • Use references/initialization-manifest.md as the single source for initialization inventory.
   • Follow idempotent behavior: create missing files/directories, preserve existing files unless explicit update is requested.
   • Check AGENTS.md then CLAUDE.md; if both exist or neither exists, ask user which file to append, then append section from references/agents-lessons-section.md.
2. Mandatory lesson review for this harvest run:
   • Read docs/notes/00-INDEX.md when available.
   • Scan docs/notes/mocs/lessons-learned.md when available.
   • Apply matched lessons (tech, operation type, error pattern).

Phase 2: Detect + Route

1. Build context_id:
   • First env var that matches *SESSION*ID*, *CONVERSATION*ID*, or *THREAD*ID* (case-insensitive).
   • Fallback timestamp YYYYMMDDHHmmss.
2. Look for docs/notes/contexts/<context_id>-*.md.

Phase 3: New Context

1. Extract high-signal items: work, decisions (with rationale), unsolved, lessons, optional source notes.
   • Use stable item IDs for merge safety: D-*, Q-*, LL-*.
   • If planning files (task_plan.md, findings.md, progress.md) are present, capture medium-density snapshots (conclusion + evidence + source note) into context content.
   • Do not copy full planning files. Do not create Obsidian wikilinks to files outside docs/notes/.
2. Generate filename <context_id>-<topic-slug>.md and confirm:

Found: [N] decisions, [N] unsolved, [N] lessons
Suggested: contexts/<context_id>-<topic-slug>.md
1. Use this  2. Change slug  3. Cancel

3. Create docs/notes/contexts/<filename>.md from references/context-template.md.
4. Use obsidian-markdown when available for wikilinks/frontmatter/anchors.
5. Update docs/notes/00-INDEX.md according to references/index-template.md:
   • Recent Updates (top 5), Topics, Key Decisions, Open Questions, Recent Lessons, Stats.
6. Manage MOCs:
   • Lessons MOC: for error-related lessons (>15 min impact), ensure docs/notes/mocs/lessons-learned.md exists via references/lessons-learned-moc-template.md, then append links only.
   • Topic MOC: when a topic appears in 3+ contexts without MOC, ask user first; create from references/moc-template.md after confirmation.
7. Confirm:

✓ Created: contexts/<filename>.md
✓ Updated: 00-INDEX.md
✓ Updated: mocs/lessons-learned.md (when relevant)
✓ Created: mocs/<topic>.md (when relevant)

Phase 4: Smart Merge

1. Read the existing context file.
2. Merge new items from current conversation.

3. Update frontmatter (updated, tags), keep created unchanged.
4. Update 00-INDEX.md stats and recent updates.
5. Update mocs/lessons-learned.md with links only when new error-related lessons were added.
6. Confirm:

✓ Updated: contexts/<filename>.md
Changes: [added/updated/moved items]

Content Quality Rules

• Quality over quantity: concise, reusable, high-signal notes.
• One idea per bullet; include rationale for decisions.
• Keep content relevant for future reuse (3+ months horizon).
• Skip raw transcripts, dead ends without insight, and obvious process noise.
• Use stable IDs (D-*, Q-*, LL-*) with anchored headings for merge-safe entries.
• For lessons, include: what happened, root cause, solution, guardrail, apply-when.
• For carry-over items from prior sessions, label clearly and avoid presenting them as new outcomes.
• For planning-derived content, store medium-density snapshots (conclusion + evidence + source note) in context files; avoid external-file wikilinks outside docs/notes/.

Recommended section limits:

Integration

Recommended: obsidian-markdown skill for enhanced Obsidian compatibility. Without it, AI may write files directly and suggest installation:

For optimal Obsidian compatibility, consider installing obsidian-markdown skill:
npx skills add <obsidian-markdown-repo>

Optional companion: planning-with-files for stronger in-progress capture.

• Harvest remains fully functional without it.
• When available, Harvest may consume planning outputs (task_plan.md, findings.md, progress.md) as snapshot sources, then persist reusable knowledge into docs/notes/contexts/.
• Prefer provenance text over external links when planning files are outside Obsidian vault scope.

See Also

Use these files as references (single source for structure and formats).

• context-template.md
• moc-template.md
• index-template.md
• lessons-learned-moc-template.md
• contexts-base-template.base
• mocs-base-template.base
• agents-lessons-section.md
• initialization-manifest.md