EdgeQuake is a Rust framework that turns documents into knowledge graphs for GraphRAG, a retrieval-and-generation approach that uses linked facts to help language models find relevant information. It is used to build applications that search and generate answers from document collections.
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 skills add raphaelmansuy/edgequake --skill explain-papergit clone --depth 1 https://github.com/raphaelmansuy/edgequakeWrote 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/skills/raphaelmansuy/edgequake/explain-paper)<a href="https://agentmods.dev/skills/raphaelmansuy/edgequake/explain-paper"><img src="https://agentmods.dev/badge/skills/raphaelmansuy/edgequake/explain-paper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/raphaelmansuy/edgequake/explain-paper"><img src="https://agentmods.dev/badge/skills/raphaelmansuy/edgequake/explain-paper.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00148 |
| Opus 5.5 | $0.00000 | $0.00059 |
| Sonnet 5.5 | $0.00000 | $0.00030 |
| Haiku 4.5 | $0.00000 | $0.00015 |
Grade A, and why
explain-paper 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 16d 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
Skill: explain a paper
Use EdgeQuake MCP tools as evidence — never invent document lists.
eq_document_list— find the PDF byfile_name/ title.- Call
eq_searchwithdocument_ids: [<id>]and a focused query. eq_fetch(view=toc)on theretrieval_id.- Escalate to
view=chunksoreq_neighborhoodonly if needed. - If
truncation.truncated, follownext_cursorbefore concluding the corpus is small. - Cite
document_id+ chunk/page from the tool results. Do not claim an LLM essay from EdgeQuake.
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.
- 16d ago First seen · 11 lines · 0 tokens per session scan A 9180c0d479cd
explain-paper is a skill published in the GitHub repository raphaelmansuy/edgequake (2,261 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 148 tokens. 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 2026-09-30.
Other skills, from other repositories
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
rag-mcp-tool-selection
Select the top-K tools from a registry of 30+ MCP / AWS / internal-API tools for a given natural-language query, replacing MCP's tools/list dump with a RAG-style filter that reduces prompt tokens 50-70%. Three-step pipeline: retrieve / validate / format. Use when the agent has access to many tools and prompt bloat is…
rrf-hybrid-retrieval
Reciprocal Rank Fusion (RRF) hybrid retrieval across 4 parallel channels — semantic / keyword / graph-traversal / temporal — followed by cross-encoder rerank and token-budget filter (HINDSIGHT, Latimer et al. 2025, cited in Ch4). Rank-based fusion means scores don't need calibration across channels; absent items…
vector-vs-graph-retrieval-selector
Recommend VECTOR / GRAPH / HYBRID retrieval for a query workload, grounded in Ch1's BenchmarkQED evidence for where vector RAG succeeds and where it collapses. Classifies the workload on the BenchmarkQED scope x type axes (local/global, data/activity), weighs multi-hop / temporal / associativity needs, domain…
three-graph-router
Route an incoming record/fact into the correct graph of the Three-Graph Architecture (Ch3) — DOMAIN (trusted, entity-resolved single source of truth), LEXICAL (verbatim source text with provenance, the "retrieval" in RAG), or SUBJECT (LLM-extracted artifacts kept SEPARATE from domain until entity resolution links…
rag-setup-project
Set up LightRAG persistent memory for a Cursor project with MCP configuration.