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.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 | $0.00044 | $0.00539 |
| Opus 5 | $0.00022 | $0.00269 |
| Sonnet 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 4d 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.
- 4d ago Changed 3f1599c1b5a4
- 8d 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 (5 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 539 once invoked, about $0.0002 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 commands, from other repositories
octo-docs
Document delivery with export to PPTX, DOCX, PDF formats.
latex-polish
Inspect a cleanly compiling LaTeX document for source pathologies and rendered visual defects by linting and viewing selected PDF pages. Use when compilation succeeds but title pages, floats, tables, figures, or layout still need publication-quality review. Not for basic compilation health; use $latex-health-check.
latex
Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or…
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.
bib-parse
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.