Pipeline

EXECUTE NOW

Target: $ARGUMENTS

Parse immediately:

• Source file path: the file to process (required)
• --handoff: output RALPH HANDOFF block at end (for chaining)
• If target is empty: list files in {DOMAIN:inbox}/ and ask which to process

Step 0: Read Vocabulary

Read ops/derivation-manifest.md (or fall back to ops/derivation.md) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.

START NOW. Run the full pipeline.

Pipeline Overview

The pipeline chains four phases. Each phase uses skill invocation or /ralph for subagent-based processing. State lives in the queue file — the pipeline is stateless orchestration on top of stateful queue entries.

Source file
    |
    v
Phase 1: /seed — create extract task, move source to archive
    |
    v
Phase 2: /reduce (via /ralph) — extract claims from source
    |
    v
Phase 3: /ralph (all claims) — create -> reflect -> reweave -> verify
    |
    v
Phase 4: /archive-batch — move task files, generate summary
    |
    v
Complete

The pipeline is the convenience wrapper. /ralph is the engine. /seed is the entry point.

Phase 1: Seed

Invoke /seed on the target file to create the extract task, check for duplicates, and move the source to its archive folder.

How to invoke:

Use the Skill tool if available, otherwise execute the /seed workflow directly:

• Validate source exists
• Check for prior processing (duplicate detection)
• Create archive folder
• Move source from {DOMAIN:inbox} to archive
• Create extract task file
• Add extract task to queue

Capture from seed output:

• Batch ID: the source basename (used for --batch filtering in subsequent steps)
• Archive folder path: where the source was moved
• next_claim_start: the claim numbering start

Report: $ Seeded: {source-name}

If seed reports the file was already processed: Ask the user whether to proceed or skip. Do NOT auto-skip — the user may want to re-process with different scope.

Phase 2: Extract (Reduce)

Process the extract task via /ralph. This spawns a subagent that runs /reduce, extracting claims from the source and creating task entries in the queue.

How to invoke:

/ralph 1 --batch {batch_id} --type extract

Or via Task tool:

Task(
  prompt = "Run /ralph 1 --batch {batch_id} --type extract",
  description = "extract: {batch_id}"
)

After completion, read the queue to count extracted claims and enrichments:

Check how many pending tasks exist for this batch. The reduce phase creates 1 queue entry per claim and 1 per enrichment.

Report:

$ Extracted: {N} {DOMAIN:note_plural}, {M} enrichments
  Processing {total_tasks} tasks through the pipeline...

If zero claims extracted: Report the issue. For TFT sources, zero extraction is a bug — the source almost certainly contains extractable content. Ask the user whether to retry with different scope or skip.

Phase 3: Process All Claims

Count total pending tasks for this batch from the queue. Then process all of them through the full phase sequence.

How to invoke:

/ralph {remaining_count} --batch {batch_id}

Or via Task tool:

Task(
  prompt = "Run /ralph {remaining_count} --batch {batch_id}",
  description = "process: {batch_id} ({remaining_count} tasks)"
)

This processes every claim through: create -> reflect -> reweave -> verify. And every enrichment through: enrich -> reflect -> reweave -> verify.

Each phase runs in an isolated subagent with fresh context. /ralph handles all the orchestration: subagent spawning, handoff parsing, queue advancement, learnings capture.

Progress reporting:

The /ralph invocation reports progress per task. The pipeline relays this:

$ Processing {DOMAIN:note} 1/{total}: {title}
  $ create... done
  $ reflect... done (3 connections found)
  $ reweave... done (2 {DOMAIN:note_plural} updated)
  $ verify... done (PASS)

For large batches (20+ claims): /ralph handles context isolation automatically via subagents. The pipeline does NOT need to chunk — /ralph processes N tasks sequentially with fresh context per phase.

Phase 4: Verify Completion

After /ralph finishes, verify all tasks for this batch are done.

Check the queue: count tasks for this batch that are NOT done.

If tasks remain pending:

• Report which tasks are incomplete and at which phase
• Show the specific task IDs and their current_phase
• Suggest: "Run /ralph --batch {batch_id} to continue from where it stopped"
• Do NOT proceed to archive

If all tasks are done: Proceed to Phase 5.

Phase 5: Archive Batch

When all tasks for the batch are complete, archive the batch.

How to invoke:

/archive-batch {batch_id}

Or execute directly:

1. Move all task files from ops/queue/ to ops/queue/archive/{date}-{batch_id}/
2. Generate a batch summary file: {batch_id}-summary.md
3. Remove completed entries from the queue (or mark as archived)

The summary should include:

• Source file name and original location
• Number of claims extracted
• Number of enrichments
• List of created {DOMAIN:note_plural} with titles
• Any notable learnings from the batch