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.
git 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/commands/roomi-fields/paper-trail/paper-trail-cascade)<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-cascade"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-cascade/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-cascade"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-cascade.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.00539 |
| Opus 5.5 | $0.00018 | $0.00216 |
| Sonnet 5.5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
paper-trail-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 1mo 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.
What it actually says
/paper-trail:cascade — Run the PDF acquisition cascade
Invoke the pdf-cascade skill to push refs through the FSM via the
strict acquisition cascade.
Usage
/paper-trail:cascade <slug> # one ref by slug
/paper-trail:cascade --state candidate # batch by state
/paper-trail:cascade --state candidate --limit 20
/paper-trail:cascade --ref <slug> --dry-run
What it does
-
Parses the argument (slug,
--state X, optional--limit N,--dry-run,--cited-in <SOTA_name>) -
Invokes the worker B :
python -m pipeline run <args> -
Reports session recap :
planned / done / pending / blocked / skipped_terminal -
Each acquired PDF is validated page 1 anti-homonymy automatically before being accepted
-
Doctor runs at the end (unless
--no-doctor) to flag any new invariant violation
Shadow libraries
By default, the cascade has 10 sources (no Sci-Hub, no Anna's Archive).
To enable shadow libs for this session (cf. DISCLAIMER.md) :
export RESEARCH_ENABLE_SHADOW_LIBS=1
/paper-trail:cascade --state candidate --limit 10
The cascade then has 15 sources — 17 with the browser routes available
as well (Playwright + a display, see docs/ACQUISITION_HEADFUL.md).
A disclaimer prints to stderr at the first cascade load of the session.
Output trace
Every attempt is logged in the registry under acquisition_attempts[] :
acquisition_attempts:
- n: 1
source: crossref_oa
verdict: no_source
reason: no_doi
- n: 2
source: arxiv
verdict: success
pdf_path: 13_Biblio_Maths/Sources/Smith_2020.pdf
pdf_sha256: a3f5...
Use /paper-trail:status to see overall registry state, or
/paper-trail:doctor to verify post-cascade consistency.
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.
- 1mo ago Changed 3f1599c1b5a4
- 1mo ago First seen · 69 lines · 44 tokens per session scan A e33eb9e9727a
paper-trail-cascade is a command published in the GitHub repository roomi-fields/paper-trail (6 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 539 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
octo-docs
Document delivery with export to PPTX, DOCX, PDF formats.
print-audit
Audit a print layout for bleed, safe zone, color mode, font embedding, and page break rules. Optionally audits brand consistency when brand context is provided.
pdf-report
Generate a multi-page print-ready report or document layout with page geometry, master template, typography system, and CSS @media print + @page output.
print-layout
Design a single print artifact (business card, flyer, certificate, brochure, invoice) with correct bleed, safe zone, CMYK color system, and print-ready HTML/CSS output.
doc-to-md
Convert a PDF, docx, image, or other document to clean Markdown using Antigravity (agy) multimodal Gemini. Saves to docs/agy/converted/.
bib-filter
Filter a LaTeX project's bibliography to the entries actually cited, with Overleaf-source resolution, temporary staging, validation, approval-gated canonical replacement, and compilation. Use before submission or after large revisions.