# Pipeline

End-to-end source processing -- seed, reduce, process all claims through...

- Repository: https://github.com/agenticnotetaking/arscontexta (3518 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-02-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add agenticnotetaking/arscontexta --skill pipeline -g -a claude-code -y`
Codex: `npx skills add agenticnotetaking/arscontexta --skill pipeline -g -a codex -y`
Cursor: `npx skills add agenticnotetaking/arscontexta --skill pipeline -g -a cursor -y`
Gemini CLI: `npx skills add agenticnotetaking/arscontexta --skill pipeline -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add agenticnotetaking/arscontexta`

## Description

End-to-end source processing -- seed, reduce, process all claims through reflect/reweave/verify, archive. The full pipeline in one command. Triggers on "/pipeline", "/pipeline [file]", "process this end to end", "full pipeline".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

## 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}`

The rest: https://github.com/agenticnotetaking/arscontexta/blob/HEAD/skill-sources/pipeline/SKILL.md