niobium-client: Instructions file for Codex

AGENTS.md

niobium-client AGENTS.md is an instructions file for Codex, OpenCode from NiobiumInc/niobium-client. It costs 1,880 tokens per session, scanned A, original, Apache-2.0.

A project-specific guide for Niobium Client, an open-source client stack for developing applications that use fully homomorphic encryption, which lets computations run on encrypted data.

In plain words
What is it for?
It helps plan FHE applications, choose encryption settings, validate a plain reference version, and work with Niobium’s DSL, examples, or intermediate representation.
Why use it?
It tells coding agents which design process, tools, and project areas to use before changing encryption-related code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is NiobiumInc/niobium-client's own configuration. It tells Codex and OpenCode how to work on niobium-client itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything niobium-client configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NiobiumInc/niobium-client. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NiobiumInc/niobium-client/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/NiobiumInc/niobium-client

Made for: Codex, OpenCode.

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 niobium-client AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/niobiuminc/niobium-client/agents-md/github.svg)](https://agentmods.dev/instructions/niobiuminc/niobium-client/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/niobiuminc/niobium-client/agents-md"><img src="https://agentmods.dev/badge/instructions/niobiuminc/niobium-client/agents-md/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 niobium-client AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/niobiuminc/niobium-client/agents-md"><img src="https://agentmods.dev/badge/instructions/niobiuminc/niobium-client/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,880 This file is loaded in full into every session.
When invoked 1,880 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01880 $0.01880
Opus 5 $0.00940 $0.00940
Sonnet 5 $0.00376 $0.00376
Haiku 4.5 $0.00188 $0.00188

Measured 9d ago against content hash 9bdc7f32d9f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

niobium-client AGENTS.md 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.

AGENTS.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for Claude Code (and other agents) working in this repository.

Designing or building an FHE application? Install and follow the fhe-application-design skill — do not skip the design stages. It walks privacy model, feasibility, scheme and parameter selection, a plaintext twin validated against your own reference computation, then the encrypted program and its Fog deployment. This applies whether you enter through the nb DSL (dsl_fhe/), instrumented OpenFHE (examples/), or direct FHETCH IR — the design work comes before the code either way.

The skill is installed on demand, not committed: run make sync-skill to install it into .claude/skills/ (Claude Code) and .agents/skills/ (Open Agent standard: Codex, Cursor, Copilot, Gemini, and others), both gitignored; once installed it auto-loads. End users of the catalog can instead run npx skills add NiobiumInc/niobium-skills --skill fhe-application-design.

Project Overview

Niobium Client is the open-source client stack for the Niobium Mistic FHE accelerator, with four entry points converging on one FHETCH Polynomial IR trace: the nb DSL + design skill (AI-agent coding, dsl_fhe/ + the fhe-application-design skill), instrumented OpenFHE (application developers, examples/), direct FHETCH IR emission (compiler writers, via libnbfhetch + src/fhetch_transport/), and HAZE (FHE library integrators, CUDA-shaped C API, vendor/niobium-haze). It wires the Niobium-instrumented OpenFHE branch to the FHETCH recording/replay library (libnbfhetch, vendored from niobium-fhetch) and ships end-to-end OpenFHE examples.

A customer links their OpenFHE C++ app against the instrumented OpenFHE + libnbfhetch, brackets the computation with niobium::compiler() calls, runs it to capture an unoptimized .fhetch instruction trace, and either replays the trace locally through the bundled simulator (fhetch_sim) to reconstruct the result ciphertext, or submits it to the Niobium compilation service. This repo does not contain the proprietary compiler.

Read the full file on GitHub · 136 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 · 136 lines · 1,880 tokens per session scan A 9bdc7f32d9f7

Subscribe to this mod's changes

niobium-client AGENTS.md is an instructions file published in the GitHub repository NiobiumInc/niobium-client (20 stars, last pushed today), licensed Apache-2.0. It adds 1,880 tokens to every session, about $0.0094 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens