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 commands/usathyan/epistract/ingestgit clone --depth 1 https://github.com/usathyan/epistractWrote 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/usathyan/epistract/ingest)<a href="https://agentmods.dev/commands/usathyan/epistract/ingest"><img src="https://agentmods.dev/badge/commands/usathyan/epistract/ingest.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 | $0.00017 | $0.02552 |
| Opus 5 | $0.00009 | $0.01276 |
| Sonnet 5 | $0.00003 | $0.00510 |
| Haiku 4.5 | $0.00002 | $0.00255 |
Grade A, and why
epistract-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 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epistract Document Ingestion Pipeline
You are running the epistract drug discovery knowledge graph pipeline.
Usage Guard
If invoked with no arguments or with --help: Display the following usage block verbatim and stop — do not run any pipeline steps.
Usage: /epistract:ingest <corpus-dir> [options]
Required:
<corpus-dir> Directory or file path containing documents to ingest (PDF, DOCX, HTML, TXT, and 75+ formats)
Options:
--domain <name> Domain schema to use (default: drug-discovery; choices: drug-discovery, contracts, clinicaltrials)
--output <dir> Output directory (default: ./epistract-output)
--validate Enable molecular validation (auto-enabled if RDKit is installed)
--view Open graph viewer after build (default: true)
--fail-threshold <float> Minimum extraction pass rate before graph build (default: 0.95, range: 0.0–1.0)
--enrich Enrich graph via external APIs after build — clinicaltrials domain only
(Trial nodes → ClinicalTrials.gov v2; Compound nodes → PubChem PUG REST)
Examples:
/epistract:ingest ./my-papers
/epistract:ingest ./papers --domain clinicaltrials --enrich
/epistract:ingest ./papers --domain contracts --output ./out --fail-threshold 0.9
Arguments
path(required): Directory or file path containing documents--output(optional): Output directory (default: ./epistract-output)--domain(optional): Domain name for extraction (default: drug-discovery). Choices:drug-discovery,contracts,clinicaltrials. Aliases (contract,clinicaltrial,clinical_trials) resolve automatically.--validate(optional): Enable molecular validation (default: true if rdkit installed)--view(optional): Open viewer after build (default: true)--fail-threshold <float>(optional): Minimum post-normalization pass rate required before graph build (default: 0.95, range: [0.0, 1.0]). Pipeline aborts with a clear error if the pass rate falls below this threshold.--enrich(optional flag): When present AND--domainisclinicaltrials(or aliasesclinicaltrial/clinical_trials), triggers post-build enrichment against ClinicalTrials.gov v2 and PubChem PUG REST APIs. Trial nodes with NCT IDs get trial metadata; Compound nodes get molecular data. Non-blocking: API failures log counts but do not abort the pipeline.
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 First seen · 187 lines · 17 tokens per session scan A 901592fb4bd6
epistract-ingest is a command published in the GitHub repository usathyan/epistract (8 stars, last pushed 19d ago), licensed MIT. It adds 17 tokens to every session and 2,552 once invoked, about $0.0001 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
master_analysis
Run comprehensive 5-phase analysis across labs, genetics, and protocols.
render-figures
Compile all .tex and .typ figure files in a directory.
replication-package
Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
arg-diagram
ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.
simulation-calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.