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/dashboardgit 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/dashboard)<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>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 | $0.00025 | $0.01536 |
| Opus 5 | $0.00013 | $0.00768 |
| Sonnet 5 | $0.00005 | $0.00307 |
| Haiku 4.5 | $0.00003 | $0.00154 |
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.
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:
- Chat panel — ask natural-language questions of the graph, answers streamed with citations back to source documents
- Graph panel — force-directed interactive visualization with community coloring, entity-type filters, and relation-type toggles
- 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
- Chat panel — ask natural-language questions of the graph, answers streamed with citations back to source documents
- Graph panel — force-directed interactive visualization with community coloring, entity-type filters, and relation-type toggles
- Sources panel — drill into the underlying documents, entities, and relations that ground each answer
Arguments
Arguments
<output_dir>(required) — directory containinggraph_data.json,communities.json, and (optionally)claims_layer.jsonfrom a prior/epistract:ingest+/epistract:epistemicrun--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--domainflag wins, thengraph_data.json.metadata.domainauto-detection, then generic fallback. If you pass--domain fooagainst 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 nometadata.domainand 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)
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.
- 3d ago First seen · 104 lines · 25 tokens per session scan A d177fa7452bc
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.