epistract-dashboard

epistract-dashboard is a command for coding agents from usathyan/epistract. It costs 25 tokens per session (1,536 once invoked), scanned A, original, MIT.

A local web workbench for exploring an existing Epistract knowledge graph. It combines question-and-answer chat with source citations, an interactive connected-node graph, and a panel for inspecting the underlying documents and relationships.

In plain words
What is it for?
Ask questions about a graph, filter entities and relationships, view communities, and inspect the documents, entities, and relationships supporting an answer.
Why use it?
It brings answers, visual connections, and supporting source material into one place, making it easier to check where information came from.

Command

Part of the epistract plugin — 5 skills, 22 commands, 3 agents shipped together

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/dashboard
Clone the repo
git clone --depth 1 https://github.com/usathyan/epistract

Or install epistract, the plugin that ships this one along with the rest of its 5 skills, 22 commands, 3 agents.

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.

agentmods badge for epistract-dashboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/usathyan/epistract/dashboard.svg)](https://agentmods.dev/commands/usathyan/epistract/dashboard)
Your own site
<a href="https://agentmods.dev/commands/usathyan/epistract/dashboard"><img src="https://agentmods.dev/badge/commands/usathyan/epistract/dashboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,536 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 $0.00025 $0.01536
Opus 5 $0.00013 $0.00768
Sonnet 5 $0.00005 $0.00307
Haiku 4.5 $0.00003 $0.00154

Measured 3d ago against content hash d177fa7452bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

epistract-dashboard 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 3d 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/dashboard.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epistract Dashboard — Interactive Workbench

Launch the FastAPI-backed workbench for an existing knowledge graph. The workbench serves three synchronized panels:

  1. Chat panel — ask natural-language questions of the graph, answers streamed with citations back to source documents
  2. Graph panel — force-directed interactive visualization with community coloring, entity-type filters, and relation-type toggles
  3. Sources panel — drill into the underlying documents, entities, and relations that ground each answer

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:dashboard <output-dir> [options]

Required:
  <output-dir>    Path to directory containing graph_data.json

Options:
  --domain <name>    Domain for branding and entity colors  (default: auto-detected from graph_data.json)
  --port <n>         Port to serve on  (default: 8000)
  --host <addr>      Host address      (default: 127.0.0.1)

Examples:
  /epistract:dashboard ./epistract-output
  /epistract:dashboard ./out --domain clinicaltrials --port 8080
  /epistract:dashboard ./out --host 0.0.0.0 --port 3000
  1. Chat panel — ask natural-language questions of the graph, answers streamed with citations back to source documents
  2. Graph panel — force-directed interactive visualization with community coloring, entity-type filters, and relation-type toggles
  3. Sources panel — drill into the underlying documents, entities, and relations that ground each answer

Arguments

Arguments

  • <output_dir> (required) — directory containing graph_data.json, communities.json, and (optionally) claims_layer.json from a prior /epistract:ingest + /epistract:epistemic run
  • --domain <name> (optional) — domain package name (e.g., drug-discovery, contracts). Loads domain-specific workbench template (title, entity colors, persona prompt). Precedence (per FIDL-06): explicit --domain flag wins, then graph_data.json.metadata.domain auto-detection, then generic fallback. If you pass --domain foo against a graph built with --domain bar, the flag wins — this is intentional so you can experiment with alternate templates against the same graph. Legacy graphs built before Phase 17 have no metadata.domain and fall back to generic with a one-line warning on stderr; rebuild with /epistract:ingest --domain <name> to silence it.
  • --port <port> (optional) — HTTP port (default: 8000)
  • --host <host> (optional) — bind host (default: 127.0.0.1 for localhost-only)

Read the full file on GitHub · 104 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.

  1. 3d ago First seen · 104 lines · 25 tokens per session scan A d177fa7452bc

Subscribe to this mod's changes

epistract-dashboard is a command published in the GitHub repository usathyan/epistract (8 stars, last pushed 18d ago), licensed MIT. It adds 25 tokens to every session and 1,536 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.