Loading source
Pulling the file list, source metadata, and syntax-aware rendering for this listing.
Source from repo
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.
Files
Skill
Size
Entrypoint
Format
Open file
Syntax-highlighted preview of this file as included in the skill package.
researcher/queue/README.md
1# Researcher Queue23The queue files are the persistent ledger that lets the autonomous loop run for days without losing state. Every change is append-only or replaces the entire file with a new sorted snapshot.45## Files67- `inbox.jsonl` - candidate sources discovered but not yet initialized as runs.8- `parked.jsonl` - run IDs that hit a human-review gate and are waiting for a reviewer.9- `done.jsonl` - run IDs that have been closed (accepted, rejected, reference-only, abandoned).10- `quarantine.jsonl` - sources removed from rotation because retrieval failed or the source registry rejects them.1112## Source Record Shape1314Each line in `inbox.jsonl` and `quarantine.jsonl` is a JSON object:1516```json17{18"source_id": "deterministic-hash",19"url": "https://example.com/post",20"title": "Short title",21"author_or_org": "Org",22"source_type": "paper | engineering_blog | documentation | benchmark | code | talk | other",23"candidate_reason": "Why this source matters",24"feed": "manual-seed | parallel-research | rss | other",25"discovered_at": "ISO-8601",26"attempts": 0,27"last_status": "queued | initialized | failed"28}29```3031Active runs live under `researcher/runs/<run-id>/` and have their own `run-state.json`. The loop scripts read those state files directly rather than duplicating active-run state here, so there is one source of truth per run.32