seed

1## EXECUTE NOW
2 
3**Target: $ARGUMENTS**
4 
5The target MUST be a file path. If no target provided, list {DOMAIN:inbox}/ contents and ask which to seed.
6 
7### Step 0: Read Vocabulary
8 
9Read `ops/derivation-manifest.md` (or fall back to `ops/derivation.md`) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.
10 
11**START NOW.** Seed the source file into the processing queue.
12 
13---
14 
15## Step 1: Validate Source
16 
17Confirm the target file exists. If it does not, check common locations:
18- `{DOMAIN:inbox}/{filename}`
19- Subdirectories of {DOMAIN:inbox}/
20 
21If the file cannot be found, report error and stop:
22```
23ERROR: Source file not found: {path}
24Checked: {locations checked}
25```
26 
27Read the file to understand:
28- **Content type**: what kind of material is this? (research article, documentation, transcript, etc.)
29- **Size**: line count (affects chunking decisions in /reduce)
30- **Format**: markdown, plain text, structured data
31 
32## Step 2: Duplicate Detection
33 
34Check if this source has already been processed. Two levels of detection:
35 
36### 2a. Filename Match
37 
38Search the queue file and archive folders for matching source names:
39 
40```bash
41SOURCE_NAME=$(basename "$FILE" .md | tr ' ' '-' | tr '[:upper:]' '[:lower:]')
42 
43# Check queue for existing entry
44# Search in ops/queue.yaml, ops/queue/queue.yaml, or ops/queue/queue.json
45grep -l "$SOURCE_NAME" ops/queue*.yaml ops/queue/*.yaml ops/queue/*.json 2>/dev/null
46 
47# Check archive folders
48…