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-inject-url)<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-inject-url"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-inject-url/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-inject-url"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-inject-url.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 | $0.00041 | $0.00766 |
| Opus 5 | $0.00020 | $0.00383 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
paper-trail-inject-url 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 10d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/paper-trail:inject-url <slug> <url> — URL OA fournie manuellement
Quand la cascade automatique épuise toutes ses sources mais que vous savez où le PDF est disponible (page d'auteur, dépôt universitaire, HAL, NIME, eScholarship…), cette commande injecte l'URL dans le frontmatter de la ref puis relance la cascade. Aucun bricolage manuel.
Le résolveur landing→PDF du pipeline suit automatiquement la balise
<meta name="citation_pdf_url"> (norme Highwire Press), donc une URL
de page de dépôt fonctionne — pas besoin du PDF direct.
Usage
/paper-trail:inject-url <slug> <url>
Exemple :
/paper-trail:inject-url murgul_2024_polyrhythm \
https://publikationen.bibliothek.kit.edu/1000183782
Ce que fait Claude
-
Vérifie la ref : la ref
<slug>doit exister dans le registre et être en étatuid_resolved,needs_reacquisition, oublocked_human:cascade_exhausted_needs_manual. Sinon refuse en expliquant. -
Écrit
oa_url:dans le frontmatter :python3 -c " import sys; sys.path.insert(0, 'pipeline') from pipeline.registry import load_ref, save_ref r = load_ref('<slug>') r.frontmatter['oa_url'] = '<url>' save_ref(r) " -
Si la ref était bloquée, débloque-la pour que la cascade puisse la reprendre :
python3 -m pipeline arbitrate <slug> --decision unblock \ --reason "manual oa_url provided" -
Relance la cascade ciblée :
python3 -m pipeline run --ref <slug>La nouvelle source
manual_oa_urlest en tête de cascade donc essayée en premier. -
Récap : si succès, affiche le chemin PDF + sha256 ; sinon liste ce qui a échoué (HTTP 404, page sans
citation_pdf_url, validation page 1 KO, etc.) et propose les pistes du fichier_hints/<slug>.mdgénéré automatiquement.
Quand utiliser
- Le fichier
_hints/<slug>.mda été généré (la cascade a épuisé) ET vous connaissez une URL OA fiable. - Plus rapide que de télécharger le PDF à la main puis renseigner
pdf_pathmanuellement.
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.
- 10d ago First seen · 96 lines · 41 tokens per session scan A 8c7c6ee823d2
paper-trail-inject-url is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 766 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.
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.
insights-deck
Archive an exported Claude Code insights HTML report and turn it into a timestamped Beamer presentation usable from either client. Use when the insights export is the source artifact for a presentation. Not for a general research talk; use $talk-deck.
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.