Reweave

Runtime Configuration (Step 0 — before any processing)

Read these files to configure domain-specific behavior:

1. ops/derivation-manifest.md — vocabulary mapping, platform hints

   • Use vocabulary.notes for the notes folder name
   • Use vocabulary.note / vocabulary.note_plural for note type references
   • Use vocabulary.reweave for the process verb in output
   • Use vocabulary.topic_map / vocabulary.topic_map_plural for MOC references
   • Use vocabulary.cmd_verify for the next-phase suggestion

2. ops/config.yaml — processing depth, pipeline chaining

   • processing.depth: deep | standard | quick
   • processing.chaining: manual | suggested | automatic
   • processing.reweave.scope: related | broad | full

If these files don't exist, use universal defaults.

Processing depth adaptation:

Reweave scope:

EXECUTE NOW

Target: $ARGUMENTS

Parse immediately:

• If target contains [[note name]] or note name: reweave that specific {vocabulary.note}
• If target contains --handoff: output RALPH HANDOFF block at end
• If target is empty: find {vocabulary.note_plural} that most need reweaving (oldest, sparsest, most outdated)
• If target is "recent" or "--since Nd": reweave {vocabulary.note_plural} not touched in N days
• If target is "sparse": find {vocabulary.note_plural} with fewest connections

Execute these steps:

1. Read the target {vocabulary.note} fully — understand its current claim, connections, and age
2. Ask the reweave question: "If I wrote this {vocabulary.note} today, with everything I now know, what would be different?"
3. If a task file exists (pipeline execution): read it to see what /reflect discovered. The Reflect section shows which connections were just added and which {vocabulary.topic_map_plural} were updated — this is your starting context for the backward pass.
4. Search for newer related {vocabulary.note_plural} — use dual discovery (semantic search + {vocabulary.topic_map} browsing) to find {vocabulary.note_plural} created AFTER the target that should connect
5. Evaluate what needs changing:
   • Add connections to newer {vocabulary.note_plural} that did not exist when this was written
   • Sharpen the claim if understanding has evolved
   • Consider splitting if the {vocabulary.note} now covers what should be separate ideas
   • Challenge the claim if new evidence contradicts it
   • Rewrite prose if understanding is deeper now
6. Make the changes — edit the {vocabulary.note} with new connections (inline links with context), improved prose, sharper claim if needed
7. Update {vocabulary.topic_map_plural} — if the {vocabulary.note}'s topic membership changed, update relevant {vocabulary.topic_map_plural}
8. If task file exists: update the {vocabulary.reweave} section
9. Report — structured summary of what changed and why
10. If --handoff in target: output RALPH HANDOFF block

START NOW. Reference below explains methodology — use to guide, not as output.

Reweave

Revisit old {vocabulary.note_plural} with everything you know today. {vocabulary.note_plural} are living documents — they grow, get rewritten, split apart, sharpen their claims. This is the backward pass that keeps the network alive.

Philosophy

{vocabulary.note_plural} are living documents, not finished artifacts.

A {vocabulary.note} written last month was written with last month's understanding. Since then:

• New {vocabulary.note_plural} exist that relate to it
• Understanding of the topic deepened
• The claim might need sharpening or challenging
• What was one idea might now be three
• Connections that were not obvious then are obvious now

Reweaving is not just "add backward links." It is completely reconsidering the {vocabulary.note} based on current knowledge. Ask: "If I wrote this {vocabulary.note} today, what would be different?"

"The {vocabulary.note} you wrote yesterday is a hypothesis. Today's knowledge is the test."

What Reweaving Can Do

Reweaving is NOT just Phase 4 of /reflect applied backward. It is a full reconsideration.

Invocation Patterns

/reweave [[note]]

Fully reconsider a specific {vocabulary.note} against current knowledge.

/reweave (no argument)

Scan for candidates needing reweaving, present ranked list.

/reweave --sparse

Process {vocabulary.note_plural} flagged as sparse by /health.

/reweave --since Nd

Reweave all {vocabulary.note_plural} not updated in N days.

How to find candidates:

# Find notes not modified in 30 days
find {vocabulary.notes}/ -name "*.md" -mtime +30 -type f

/reweave --handoff [[note]]

External loop mode for /ralph:

• Execute full workflow as normal
• At the end, output structured RALPH HANDOFF block
• Used when running isolated phases with fresh context per task

Workflow

Phase 1: Understand the {vocabulary.note} as It Exists

Read the target {vocabulary.note} completely. Understand:

• What claim does it make?
• What reasoning supports the claim?
• What connections does it have?
• When was it written/last modified?
• What was the context when it was created?

Also read the task file if one exists (pipeline execution). The task file's Reflect section shows:

• What connections /reflect just added
• Which {vocabulary.topic_map_plural} were updated
• What synthesis opportunities were flagged
• What the discovery trace looked like

This context prevents redundant work — you know what /reflect already found, so you can focus on what it missed or what needs deeper reconsideration.

Phase 2: Gather Current Knowledge (Dual Discovery)

Use the same dual discovery pattern as /reflect — {vocabulary.topic_map} exploration AND semantic search in parallel.

Path 1: {vocabulary.topic_map} Exploration — curated navigation

From the {vocabulary.note}'s Topics footer, identify which {vocabulary.topic_map}(s) it belongs to:

• Read the relevant {vocabulary.topic_map}(s)
• What synthesis exists that might affect this {vocabulary.note}?
• What newer {vocabulary.note_plural} in Core Ideas should this {vocabulary.note} reference?
• What tensions involve this {vocabulary.note}?

Path 2: Semantic Search — find what {vocabulary.topic_map_plural} might miss

Three-tier fallback for semantic search:

Tier 1 — MCP tools (preferred): Use mcp__qmd__deep_search (hybrid search with expansion + reranking):

• query: "[{vocabulary.note}'s core concepts and mechanisms]"
• limit: 15

Tier 2 — bash qmd with lock serialization: If MCP tools fail or are unavailable:

LOCKDIR="ops/queue/.locks/qmd.lock"
while ! mkdir "$LOCKDIR" 2>/dev/null; do sleep 2; done
qmd query "[note's core concepts]" --collection {vocabulary.notes_collection} --limit 15 2>/dev/null
rm -rf "$LOCKDIR"

The lock prevents multiple parallel workers from loading large models simultaneously.

Tier 3 — grep only: If both MCP and bash fail, log "qmd unavailable, grep-only discovery" and rely on {vocabulary.topic_map} + keyword search only. This degrades quality but does not block work.

Evaluate results by relevance — read any result where title or snippet suggests genuine connection.

Also check:

• Backlinks — what {vocabulary.note_plural} already reference this one? Do they suggest the target should cite back?

grep -rl '\[\[target note title\]\]' {vocabulary.notes}/ --include="*.md"

Key question: What do I know today that I did not know when this {vocabulary.note} was written?

Phase 3: Evaluate the Claim

Does the original claim still hold?

The Sharpening Test:

Read the title. Ask: could someone disagree with this specific claim?

• If yes, the claim is sharp enough
• If no, it is too vague and needs sharpening

Example:

• Vague: "context matters" (who would disagree?)
• Sharp: "explicit context beats automatic memory" (arguable position)

The Split Test:

Does this {vocabulary.note} make multiple claims that could stand alone?

• If the {vocabulary.note} connects to 5+ topics across different domains, it probably needs splitting
• If you would want to link to part of it but not all, it is a split candidate

Phase 4: Evaluate Connections

Backward connections (what this {vocabulary.note} should reference):

For each newer {vocabulary.note}, ask:

• Does it extend this {vocabulary.note}'s argument?
• Does it provide evidence or examples?
• Does it share mechanisms?
• Does it create tension worth acknowledging?
• Would referencing it strengthen the reasoning?

Forward connections (what should reference this {vocabulary.note}):

Check newer {vocabulary.note_plural} that SHOULD link here but do not:

• Do they make arguments that rely on this claim?
• Would following this link provide useful context?

Agent Traversal Check (apply to all connections):

Ask: "If an agent follows this link during traversal, what decision or understanding does it enable?"

Connections exist to serve agent navigation. Adding a link because content is "related" without operational value creates noise. Every backward or forward connection should answer:

• Does this help an agent understand WHY something works?
• Does this help an agent decide HOW to implement something?
• Does this surface a tension the agent should consider?

Reject connections that are merely "interesting" without agent utility.

Articulation requirement:

Every new connection must articulate WHY:

• "extends this by adding the temporal dimension"
• "provides evidence that supports this claim"
• "contradicts this — needs resolution"

Never: "related" or "see also"

Phase 5: Apply Changes

For pipeline execution (--handoff mode): Apply changes directly. The pipeline needs to proceed without waiting for approval.

For interactive execution (no --handoff): Present the reweave proposal first, then apply after approval.

Reweave proposal format (interactive only):

## Reweave Proposal: [[target note]]

**Last modified:** YYYY-MM-DD
**Current knowledge evaluated:** N newer {vocabulary.note_plural}, M backlinks

### Claim Assessment

[Does the claim hold? Need sharpening? Splitting? Revision?]

### Proposed Changes

**1. [change type]: [description]**

Current:
> [existing text]

Proposed:
> [new text]

Rationale: [why this change]

**2. [change type]: [description]**
...

### Connections to Add

- [[newer note A]] — [relationship]: [specific reason]
- [[newer note B]] — [relationship]: [specific reason]

### Connections to Verify (other {vocabulary.note_plural} should link here)

- [[note X]] might benefit from referencing this because...

### Not Changing

- [What was considered but rejected, and why]

---

Apply these changes? (yes/no/modify)

When applying changes:

1. Make changes atomically
2. Preserve existing valid content
3. Maintain prose flow — new links should read naturally inline
4. Verify all link targets exist
5. Update description if claim changed

The Five Reweave Actions

1. Add Connections

The simplest action. Newer {vocabulary.note_plural} exist that should be referenced.

Inline connections (preferred):

# before
The constraint shifts from capture to curation.

# after
The constraint shifts from capture to curation, and since [[throughput matters more than accumulation]], the question becomes who does the selecting.

Footer connections:

relevant_notes:
  - "[[newer note]] — extends this by adding temporal dimension"

2. Rewrite Content

Understanding evolved. The prose should reflect current thinking, not historical thinking.

When to rewrite:

• Reasoning is clearer now
• Better examples exist
• Phrasing was awkward
• Important nuance was missing

How to rewrite:

• Preserve the core claim (unless challenging it)
• Improve the path to the conclusion
• Incorporate new connections as prose
• Maintain the {vocabulary.note}'s voice