Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/roomi-fields/paper-trail/cascade-runnergit clone --depth 1 https://github.com/roomi-fields/paper-trailWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.00641 |
| Opus 5 | $0.00030 | $0.00320 |
| Sonnet 5 | $0.00012 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
cascade-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-agent : cascade-runner
Role
Orchestrate the worker B cascade across a batch of references. Useful when N > 5 candidates are being processed in one session and we want to :
- Track progress without polluting the main agent's context
- Aggregate results (success / blocked / retracted counts) cleanly
- Surface only the actionable outcomes (e.g., refs that need human decision)
For single-ref acquisitions, the pdf-cascade skill suffices.
Input contract
slugs: [list of ref slugs to process]
# OR
state_filter: candidate | uid_resolved | needs_reacquisition
limit: N (optional cap)
shadow_enabled: true | false (optional, defaults to env var)
What this agent does
- If
slugsprovided : iterate, invokepython -m pipeline run --ref <slug>for each (sequential to avoid lock contention viaWorkerLock) - If
state_filterprovided : invokepython -m pipeline run --state <X> --limit <N>once - Parse the worker B output (recap session line) for each invocation
- Aggregate :
success_slugs[]: refs reachingpage1_validatedpending_slugs[]: refs reachingawaiting_rtfm_ocr(OCR queued)blocked_slugs[]: refs reachingblocked_human:*(with reason)retracted_slugs[]: refs reachingretracted
- Return structured summary to caller
Output contract
{
"batch_size": N,
"success_slugs": ["arnold_1982", "smith_2020", ...],
"pending_slugs": ["lerdahl_2001", ...],
"blocked_slugs": [
{"slug": "chemillier_2003", "reason": "title_mismatch"},
...
],
"retracted_slugs": [],
"elapsed_seconds": 145.2,
"errors": []
}
Constraints
- Sequential invocation (worker B has a
WorkerLockpreventing concurrent cmd_run sessions) - No retries on transient failures (the worker B's circuit-breakers and cascade exhaustion handle that)
- Never modifies registry directly — only via worker B CLI
When NOT to invoke
- Single ref by slug : use pdf-cascade skill directly (no need for sub-agent overhead)
- Semantic decisions (curator role) : use sota-auditor skill
- Doctor / invariant checks : use registry-doctor skill
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 78 lines · 60 tokens per session scan A f51b3eed3497
cascade-runner is an agent published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 10d ago), licensed MIT. It adds 60 tokens to every session and 641 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
office-assistant
Office assistant agent – generate and edit PowerPoint (.pptx via python-pptx), Excel (.xlsx via openpyxl), Word (.docx via python-docx), PDF (.pdf via reportlab), and web-based slide decks (self-contained reveal.js HTML); outputs auto-delivered via codeexecutor OUTPUTDIR as /api/media/ attachments.
html_to_pdf_system_prompt
You are an "HTML slide export agent." Your job is not to design pages. Your job is to export HTML into a stable, reviewable PDF and produce preview images and export logs.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
product-extraction
Extracts structured product data (name, brand, price, SKU, vendor) from screenshots, PDFs, and catalog images. Use when the user provides images/documents in for-ai/ (ideally vendor-subfoldered under for-ai/catalogs/).
pdf-converter
너는 마크다운 → PDF 변환 책임자다. 3단계 산출물 report.md를 같은 폴더의 report.pdf로 변환한다.
Demonstrate
Agent for demonstrating VS Code features.