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/viewgit clone --depth 1 https://github.com/usathyan/epistractWhat 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 | $0.00012 | $0.00378 |
| Opus 5 | $0.00006 | $0.00189 |
| Sonnet 5 | $0.00002 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
epistract-view 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.
What it actually says
Open the interactive graph viewer. Supports optional filters.
Arguments:
output_dir-- directory with graph_data.json (default: ./epistract-output)--neighborhood <entity>-- focus on entity neighborhood--top <n>-- show top N entities by connections
python3 ${CLAUDE_PLUGIN_ROOT}/core/run_sift.py view <output_dir> [--neighborhood <entity>] [--top <n>]
Usage Guard
If invoked with --help: Display the following usage block verbatim and stop. Otherwise proceed with existing logic.
Usage: /epistract:view [output-dir] [options]
All arguments are optional — running with no arguments opens the default output directory.
Options:
<output-dir> Path to extraction output containing graph_data.json (default: ./epistract-output)
--neighborhood <entity> Show neighborhood subgraph centered on a named entity
--top <n> Limit to top N nodes by degree (default: all)
Examples:
/epistract:view
/epistract:view ./my-output
/epistract:view --neighborhood "remdesivir"
/epistract:view --top 20
Arguments:
output_dir-- directory with graph_data.json (default: ./epistract-output)--neighborhood <entity>-- focus on entity neighborhood--top <n>-- show top N entities by connections
python3 ${CLAUDE_PLUGIN_ROOT}/core/run_sift.py view <output_dir> [--neighborhood <entity>] [--top <n>]
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.
- 2d ago First seen · 47 lines · 12 tokens per session scan A 55f46937470b
epistract-view is a command published in the GitHub repository usathyan/epistract (8 stars, last pushed 17d ago), licensed MIT. It adds 12 tokens to every session and 378 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
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.