epistract-export

A command for saving a knowledge graph in common formats such as JSON, CSV, SQLite, GraphML, or GEXF.

In plain words
What is it for?
Use it to move graph data into spreadsheets, Python or R, SQL tools, or graph-visualization applications such as Gephi, yEd, and Cytoscape.
Why use it?
It lets other programs open, query, analyze, or visualize the graph instead of keeping it in one internal format.

Command

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.

agentmods
npx agentmods add commands/usathyan/epistract/export
Clone the repo
git clone --depth 1 https://github.com/usathyan/epistract
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00501
Opus 5 $0.00011 $0.00251
Sonnet 5 $0.00004 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 2d ago against content hash f2c5d9d83e4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

epistract-export 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 2d 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/export.md · 58 lines

What it actually says

Export the knowledge graph to an external format.

Arguments:

  • format -- one of: json, graphml, gexf, csv, sqlite
  • output_dir -- directory with graph_data.json (default: ./epistract-output)
python3 ${CLAUDE_PLUGIN_ROOT}/core/run_sift.py export <output_dir> <format>

Report the export path and format-specific usage tips:

  • graphml: Open in Gephi, yEd, or Cytoscape
  • sqlite: Query with SQL, DuckDB, or Datasette
  • csv: Import to Excel, pandas, or R

For OKF (Open Knowledge Format) bundles — a git-versionable markdown tree for publishing to agents/humans — use the multi-project CLI instead: python3 -m core.cli export --format okf [--project NAME] [--out DIR] [--no-evidence] [--min-confidence F].

Usage Guard

If invoked with no format argument or with --help: Display the following usage block verbatim and stop — do not run any pipeline steps.

Usage: /epistract:export <format> [output-dir]

Required:
  <format>       Export format: json, graphml, gexf, csv, or sqlite

Options:
  <output-dir>   Path to extraction output containing graph_data.json  (default: ./epistract-output)

Examples:
  /epistract:export graphml
  /epistract:export csv ./my-output
  /epistract:export sqlite
  /epistract:export json ./clinical-output

Arguments:

  • format -- one of: json, graphml, gexf, csv, sqlite
  • output_dir -- directory with graph_data.json (default: ./epistract-output)
python3 ${CLAUDE_PLUGIN_ROOT}/core/run_sift.py export <output_dir> <format>

Report the export path and format-specific usage tips:

  • graphml: Open in Gephi, yEd, or Cytoscape
  • sqlite: Query with SQL, DuckDB, or Datasette
  • csv: Import to Excel, pandas, or R
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.

  1. 2d ago First seen · 58 lines · 22 tokens per session scan A f2c5d9d83e4a

Subscribe to this mod's changes

epistract-export is a command published in the GitHub repository usathyan/epistract (8 stars, last pushed 17d ago), licensed MIT. It adds 22 tokens to every session and 501 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.