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 skills/roomi-fields/paper-trail/pdf-cascadenpx skills add roomi-fields/paper-trail --skill pdf-cascadegit clone --depth 1 https://github.com/roomi-fields/paper-trailWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/roomi-fields/paper-trail/pdf-cascade)<a href="https://agentmods.dev/skills/roomi-fields/paper-trail/pdf-cascade"><img src="https://agentmods.dev/badge/skills/roomi-fields/paper-trail/pdf-cascade.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00266 | $0.02037 |
| Opus 5 | $0.00133 | $0.01019 |
| Sonnet 5 | $0.00053 | $0.00407 |
| Haiku 4.5 | $0.00027 | $0.00204 |
Grade A, and why
pdf-cascade 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 6d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill : pdf-cascade
Purpose
Wraps the paper-trail worker B's acquisition cascade. Given a single
reference slug or a state filter, it advances the matching refs from
candidate toward page1_validated through the FSM, with strict page 1
anti-homonymy validation.
Anchors all downloads in the local registry (pdf_path, pdf_sha256,
acquisition_attempts[]) so the curator can audit everything.
When to invoke
Trigger this skill for any of:
- The user wants to fetch a PDF for a ref by slug
- The user wants to push the whole batch of
candidateoruid_resolvedrefs forward - The user explicitly calls
/paper-trail:cascade,/paper-trail:reactivate-ocr, or/paper-trail:status sota-writersub-task needs PDFs acquired for its proposed candidates
Do NOT invoke for semantic decisions (is this citation correct?) — that
belongs to sota-auditor.
How it works
The skill delegates to the worker B Python CLI:
# Single ref by slug
python -m pipeline run --ref <slug>
# Batch by state filter
python -m pipeline run --state candidate --limit 50
# Dry-run (no mutation)
python -m pipeline run --state candidate --dry-run
# Reactivate refs waiting for OCR
python -m pipeline reactivate-ocr
The CLI invokes the 8-source cascade (10 with
RESEARCH_ENABLE_SHADOW_LIBS=1 — see DISCLAIMER.md — and 11 when the
browser route is available too, see docs/ACQUISITION_HEADFUL.md). Each acquired
PDF must pass page 1 validation (author + title similarity ≥ 0.3 +
zero off-domain keywords) before being accepted into the registry.
Cascade order (default, without shadow libs)
1. Crossref OA (DOI-based, open-access metadata)
2. arXiv (preprints CS/math/physics/q-bio/q-fin/etc.)
3. OpenAlex (cross-domain academic graph)
4. Unpaywall (OA discovery, fallback)
5. HAL (Hyper Articles en Ligne, French academia)
6. CORE (UK-based open repository aggregator)
7. archive.org (digitized books and articles)
8. WebSearch queue (manual fallback — adds the ref to a queue for
human-driven search via Claude Code interactive)
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.
- 6d ago First seen · 223 lines · 266 tokens per session scan A 39fc7ef6bd33
pdf-cascade is a skill published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 2d ago), licensed MIT. It adds 266 tokens to every session and 2,037 once invoked, about $0.0013 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 skills, from other repositories
fetch-paper
Fetches a legal open-access copy of a paper from its DOI or arXiv ID — resolves through Unpaywall, arXiv PDF/HTML, and the open-access ACM Digital Library. Use when the user wants to fetch, download, read, or get the PDF or full text of a specific paper. Single polite fetch, transient processing only: it never stores…
gemini-file-analysis
Analyze files (PDFs, images, audio, video, large source files) via Gemini's multi-modal file analysis. Use when a file is too large for Claude's context or when the file is a non-text format requiring visual/audio understanding.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
add-pdf-report
Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when present, expo-sharing.
add-pdf-viewer
Internal implementation skill invoked by /add-native for native PDF control workflows. Handles HTTPS and file URI PDF viewing with @microsoft/power-apps-native-pdf-viewer 0.2.9+.
ccs-submission
Use when auditing an ACM CCS submission for HotCRP readiness, dual-cycle abstract registration and full-paper deadlines, the 12-page ACM sigconf body, anonymization, the ethics considerations appendix, artifact-availability posture, dual-submission policy, per-cycle submission caps, desk-reject triggers, and…