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/searchgit 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/search)<a href="https://agentmods.dev/commands/usathyan/epistract/search"><img src="https://agentmods.dev/badge/commands/usathyan/epistract/search.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 | $0.00023 | $0.00416 |
| Opus 5 | $0.00012 | $0.00208 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
epistract-search 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.
What it actually says
Search a project's knowledge graph and corpus. Unlike /epistract:query (which does a
substring scan of graph nodes only), this runs a BM25 full-text search over both entities
and indexed document chunks, fuses the ranked lists with reciprocal rank fusion, and can
optionally expand the results through the graph via personalized PageRank (HippoRAG 2
pattern) to surface multi-hop-related entities.
Requires a built index — run /epistract:index <project> first.
Usage Guard
If invoked with no arguments or with --help: Display the following usage block verbatim and stop.
Usage: /epistract:search <query> [options]
Required:
<query> Search terms
Options:
--project <name> Target project (default: detected from cwd or $EPISTRACT_PROJECT)
--type <type> Filter entity results by entity type
-k <n> Max results (default: 10)
--expand Graph expansion via personalized PageRank from entity hits
Examples:
/epistract:search "GLP-1 receptor agonist" --project glp1-research
/epistract:search "semaglutide" --project glp1-research --expand -k 15
/epistract:search "indemnification" --project acme-contracts --type Obligation
PYTHONPATH="${CLAUDE_PLUGIN_ROOT}" python3 -m core.cli search <query> [--project NAME] [--type TYPE] [-k N] [--expand]
Present entity hits, chunk hits (with source doc), and — if --expand was used — the
graph-expanded related entities, as formatted sections. Add --json for machine-readable output.
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 · 42 lines · 23 tokens per session scan A 992332bcf090
epistract-search is a command published in the GitHub repository usathyan/epistract (8 stars, last pushed 19d ago), licensed MIT. It adds 23 tokens to every session and 416 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
agent-brain-index
Index documents for semantic search.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
rag-publish-todo-list
Command "rag-publish-todo-list" from lucky-aeon/AgentX, covering rag 发布功能 todo list, 阶段一：数据库设计和基础架构 🗄️ ✅ 已完成, 1. 数据库表创建, 2. 领域层实现 and 3. 基础领域服务.
data
Create example data in a specific domain and upload to a Weaviate collection.
ingest
Manually add knowledge to the Weaviate store.
index
Index this repository for local RAG search, then report which rung it is on — descriptions still to write, a promotion to apply, or nothing left.