e2ee-ng

e2ee-ng is a skill for Claude Code from sparq-org/sparq. It costs 267 tokens per session (3,024 once invoked), scanned A, original, MIT.

A research-stage cryptography layer for protecting RDF data and controlling who can read, publish, or administer it. It provides the low-level formats for encrypted data blocks, commits, and recipient-wrapped secrets.

In plain words
What is it for?
Use it to implement encrypted content-addressed storage, capability-based permissions, secret sharing with X25519, and authenticated encrypted envelopes with XChaCha20-Poly1305. SPARQL queries still run locally on decrypted data.
Why use it?
It gives developers building blocks for an encrypted, local-first data store without mixing access roles or exposing stored data to a broker. It is unaudited, so its security properties have not been independently confirmed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sparq plugin — 55 skills, 20 agents, 2 hooks shipped together

Good fit Use it to implement encrypted content-addressed storage, capability-based permissions, secret sharing with X25519, and authenticated encrypted envelopes with XChaCha20-Poly1305. SPARQL queries still run locally on decrypted data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sparq-org/sparq/e2ee-ng
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.

Any agent
npx skills add sparq-org/sparq --skill e2ee-ng
Clone the repo
git clone --depth 1 https://github.com/sparq-org/sparq

Made for: Claude Code.

Or install sparq, the plugin that ships this one along with the rest of its 55 skills, 20 agents, 2 hooks.

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 e2ee-ng

README.md
[![agentmods](https://agentmods.dev/badge/skills/sparq-org/sparq/e2ee-ng/github.svg)](https://agentmods.dev/skills/sparq-org/sparq/e2ee-ng)
Your own site
<a href="https://agentmods.dev/skills/sparq-org/sparq/e2ee-ng"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/e2ee-ng/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.

agentmods 80×15 button for e2ee-ng

Your own site · 80×15
<a href="https://agentmods.dev/skills/sparq-org/sparq/e2ee-ng"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/e2ee-ng.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 267 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00267 $0.03024
Opus 5 $0.00133 $0.01512
Sonnet 5 $0.00053 $0.00605
Haiku 4.5 $0.00027 $0.00302

Measured 9d ago against content hash 324a4599f6ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

e2ee-ng 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 9d 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.

skills/e2ee-ng/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sparq-e2ee-ng — E2EE-NG profile primitives (capability / envelope / epoch)

sparq-e2ee-ng implements the low-level cryptographic primitives of the NextGraph-style E2EE-queryable profile designed in research/e2ee-nextgraph-variant-gpt56-2026-07.md (program sq-tag1q). In that profile an RDF dataset is a local-first repository: encrypted content-addressed blocks carry a causal DAG of encrypted commits; an always-on broker stores and routes opaque blocks but never sees a SPARQL request. This crate is the capability / envelope / epoch layer that everything else is built on.

Maturity (read first). RESEARCH-GRADE and externally UNAUDITED. Every confidentiality, integrity, authorization, revocation, and convergence property is designed/intended, NOT proven — the construction has had no external cryptographic review. The v0 suite name is a placeholder; production suite selection + the soundness review are gated by sq-qhy4. This crate does not claim cryptographic soundness or zero-knowledge, and it does not turn SPARQL into ciphertext-side evaluation: the profile keeps querying local over decrypted, materialized state. It is the primitives layer only — the sync, broker-protocol, CRDT, and materialization layers (design §6, §8.4–8.5) are not in this crate. Encryption + key material live only behind this crate: sparq-core / sparq-engine / sparq-substrate never link a cipher.

Quickstart

The crate is in-workspace, publish = false, so depend by path:

[dependencies]
sparq-e2ee-ng = { path = "crates/sparq-e2ee-ng" }

Seal a block and open it (the round-trip fails closed on any wrong scope):

Read the full file on GitHub · 176 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. 9d ago First seen · 176 lines · 267 tokens per session scan A 324a4599f6ec

Subscribe to this mod's changes

e2ee-ng is a skill published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 267 tokens to every session and 3,024 once invoked, about $0.0013 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens