What is paper-trail-ingest?

A command that imports the citations from one SOTA document into a reference registry. It identifies citations, finds matching publication details, removes duplicates, and can replace plain-text citations with links.

Use it to process one research document, create missing reference records, and link its citations to registry entries.

It turns scattered citation text into consistent, trackable references and lets you preview changes before applying them.

paper-trail-ingest — Command for Claude Code by roomi-fields

Install

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.

Clone the repo

git clone --depth 1 https://github.com/roomi-fields/paper-trail

Made for: Claude Code.

Or install paper-trail, the plugin that ships this one along with the rest of its 6 skills, 22 commands, 6 agents, 3 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-ingest/github.svg)](https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-ingest)

Your own site

<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-ingest"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-ingest/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/roomi-fields/paper-trail/paper-trail-ingest"><img src="https://agentmods.dev/badge/commands/roomi-fields/paper-trail/paper-trail-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 852 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00075	$0.00852
Opus 5	$0.00037	$0.00426
Sonnet 5	$0.00015	$0.00170
Haiku 4.5	$0.00007	$0.00085

Measured 9d ago against content hash 94b526703113, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

paper-trail-ingest 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 9d 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.

commands/paper-trail-ingest.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

`/paper-trail:ingest <SOTA-path>` — Ingest one SOTA

Étape 1 du pipeline cible : convertit un SOTA écrit en texte libre en un SOTA conforme (wikilinks vers refs registre).

Usage

/paper-trail:ingest <SOTA-path>                  # dry-run par défaut
/paper-trail:ingest <SOTA-path> --apply          # applique

Ce que fait Claude

Vérifie git initialisé dans le vault (sinon refuse — propose pipeline ingest --init-git la première fois).
Extrait les sections bibliographiques :
```
python3 -m pipeline ingest <SOTA-path> --extract-only
```
Retourne sur stdout un JSON [{header, is_excluded, raw_text, ...}].
Pour chaque section non exclue, invoque le sub-agent citation-parser :
```
Agent(subagent_type="citation-parser", prompt=<contenu_section_brut>)
```
Le sub-agent retourne un JSON [{author, year, title, doi?, raw, ...}].
Consolide tous les JSON de citations en un seul fichier /tmp/citations_<sota_stem>.json.
Lance l'ingestion :
```
python3 -m pipeline ingest <SOTA-path> \
    --citations-json /tmp/citations_<sota_stem>.json [--apply]
```
Sans --apply : montre ce qui serait ingéré (dry-run). Avec --apply : commit git auto, crée refs candidates, substitue le texte par [[wikilinks]].
Présente le récap intermédiaire : N nouvelles refs créées, N réutilisées, N substitutions, N skipped (low confidence), N erreurs.
Sweep automatique des textbooks incomplets (uniquement si --apply) :
- Liste les candidates :
```
python3 -m pipeline resolve-textbooks --list > /tmp/textbook_candidates_<sota_stem>.json
```
- Si le JSON est non-vide, invoque le sub-agent textbook-resolver :
```
Agent(subagent_type="textbook-resolver",
      prompt=<contenu de /tmp/textbook_candidates_<sota_stem>.json>)
```
- Sauve le JSON retourné dans /tmp/textbook_decisions_<sota_stem>.json, applique :
```
python3 -m pipeline resolve-textbooks \
    --apply-from /tmp/textbook_decisions_<sota_stem>.json
```
- Aucune décision humaine intermédiaire : le sub-agent applique ses règles documentées (agents/textbook-resolver.md) — merge / complete / blocked. Les blocked restent visibles via pipeline doctor.

Read the full file on GitHub · 84 lines

Changes

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.

9d ago First seen · 84 lines · 75 tokens per session scan A 94b526703113

Subscribe to this mod's changes

paper-trail-ingest is a command published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 6d ago), licensed MIT. It adds 75 tokens to every session and 852 once invoked, about $0.0004 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.

Claude Code Research Scientific academic-research agentic-workflow anti-hallucination citation-verification claude-code-plugin

lit-landscape

Generate figures visualizing literature trends, citation patterns, and research gaps.

Agentic-Assets/corbis-literature-starter-kit · 13 tokens

verify-citations

Verify all citations against bibliography.

Agentic-Assets/corbis-literature-starter-kit · 5 tokens

lit-review

A command for carrying out a systematic literature review, meaning a structured search and summary of research papers on a chosen topic. It also builds a citation graph showing connections between papers.

csmar432/finai-research · 0 tokens

causal-design

Design or audit the identification strategy for an observational study. Use when the task concerns estimands, causal assumptions, threats to identification, or defensible research design rather than model implementation.

flonat/flonat-research · 36 tokens

cite-check

Verify that citations actually exist and that the claims they support are faithful to the cited source. Runs deterministic existence checks (Crossref / OpenAlex / Semantic Scholar / arXiv) plus a claim-faithfulness pass via the alterlab-citation-verifier skill.

AlterLab-IEU/AlterLab-Academic-Skills · 56 tokens

proof-readability

Improve the exposition and readability of a mathematical proof already verified as correct without changing its mathematics. Use when polishing a lemma, theorem, proof, or appendix after correctness checks. Not for verifying the proof; use $verify-math.

flonat/flonat-research · 46 tokens