What is fhenix-toolkit CLAUDE.md?

Repository instructions for Fhenix Toolkit, a collection of tools for building applications that use fully homomorphic encryption, which lets some data stay encrypted while it is processed.

Use them when writing or reviewing Solidity contracts and TypeScript code that imports Fhenix encryption libraries, or when testing that code.

They explain which tool handles confidential contracts, application encryption, security reviews, and tests, reducing confusion about when each one applies.

How FhenixProtocol/fhenix-toolkit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to FhenixProtocol/fhenix-toolkit. 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/FhenixProtocol/fhenix-toolkit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/FhenixProtocol/fhenix-toolkit

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fhenixprotocol/fhenix-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/fhenixprotocol/fhenix-toolkit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/fhenixprotocol/fhenix-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/fhenixprotocol/fhenix-toolkit/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fhenixprotocol/fhenix-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/fhenixprotocol/fhenix-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,048 This file is loaded in full into every session.

When invoked 1,048 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01048	$0.01048
Opus 5.5	$0.00419	$0.00419
Sonnet 5.5	$0.00210	$0.00210
Haiku 4.5	$0.00105	$0.00105

Measured 2mo ago against content hash 35c198fac313, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fhenix-toolkit CLAUDE.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

This plugin **does not snapshot API surfaces.** When you need to know whether a specific function exists, what its current signature is, or what version a feature shipped in, **look it up live** — every skill's `referenc

CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — fhenix-toolkit

This file is read by Claude Code when this plugin is loaded. It primes Claude on how the four fhenix-* skills behave together so they activate correctly without explicit invocation.

Activation map

The skills are designed to activate from file context — Claude shouldn't need to be told which one to use. Use this table only when the user asks "which skill handles X?" or when activation seems to be missing.

Task	Skill	Trigger surface
Writing a confidential contract	`fhenix-contracts`	Solidity file imports `@fhenixprotocol/cofhe-contracts/FHE.sol`; uses `euint*` / `ebool` / `eaddress` types
Encrypting inputs, decrypting outputs, managing permits in app code	`fhenix-sdk`	TypeScript file imports `@cofhe/sdk` or any subpath (`/adapters`, `/permits`, `/web`, `/node`); hooks like `useCofhe*`
Reviewing or auditing FHE code	`fhenix-review`	PR-review prompts ("audit this", "is this safe", "look over my FHE code"); `gh pr view` output; diffs touching FHE.sol or `@cofhe/sdk`
Writing tests for FHE code	`fhenix-tests`	`.test.ts` / `.t.sol` files importing FHE.sol, `@cofhe/sdk`, `@cofhe/hardhat-plugin`, or `@fhenixprotocol/cofhe-mock-contracts`; files under `tests/contracts/`

How the skills work together

Skills are additive, not exclusive. A test file that imports both FHE.sol and @cofhe/sdk legitimately fires fhenix-contracts + fhenix-sdk + fhenix-tests. The skills are designed to layer cleanly:

fhenix-contracts and fhenix-sdk are authoring skills — they teach the right patterns.
fhenix-review is an audit lens on top of the authoring skills. It activates when the task is review (PR diff, "is this safe"), not when writing fresh code.
fhenix-tests is its own track — testing has different patterns (mocks vs plugin, deterministic seeds, multi-permit fixtures) that don't apply to authoring or review.
The fhe-reviewer subagent is invoked by fhenix-review (or directly) for deep audit passes. Use it when the diff is >200 LOC of FHE code or the merge is security-sensitive.

Read the full file on GitHub · 59 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.

2mo ago First seen · 59 lines · 1,048 tokens per session scan A 35c198fac313

Subscribe to this mod's changes

fhenix-toolkit CLAUDE.md is an instructions file published in the GitHub repository FhenixProtocol/fhenix-toolkit (12 stars, last pushed 21d ago), licensed MIT. It adds 1,048 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

fhenix-toolkit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fhenix-toolkit CLAUDE.mdFhenixProtocol/fhenix-toolkit	Instructions file	12	21d ago	MIT	A	1,048	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

fhenix-toolkit: Instructions file for Claude Code