What is aurais-mcp-bots CLAUDE.md?

A set of instructions for working on an npm workspaces monorepo, which is one repository containing several related packages. It documents the project layout, commands, and conventions for six Vorion packages.

Use it when working on the five Aurais MCP servers or the proof-verifier package, including installation, testing, and build tasks.

It gives coding agents and developers the project context needed to change, test, and build the packages consistently.

How vorionsys/aurais-mcp-bots configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vorionsys/aurais-mcp-bots. 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/vorionsys/aurais-mcp-bots/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vorionsys/aurais-mcp-bots

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/vorionsys/aurais-mcp-bots/claude-md/github.svg)](https://agentmods.dev/instructions/vorionsys/aurais-mcp-bots/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vorionsys/aurais-mcp-bots/claude-md"><img src="https://agentmods.dev/badge/instructions/vorionsys/aurais-mcp-bots/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/vorionsys/aurais-mcp-bots/claude-md"><img src="https://agentmods.dev/badge/instructions/vorionsys/aurais-mcp-bots/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 636 This file is loaded in full into every session.

When invoked 636 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.

Model	Per session	Once invoked
Fable 5.1	$0.00636	$0.00636
Opus 5.5	$0.00254	$0.00254
Sonnet 5.5	$0.00127	$0.00127
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash b28228c01275, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aurais-mcp-bots CLAUDE.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 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.

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.

CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

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

What this is

An npm-workspaces monorepo that publishes six @vorionsys packages in lock-step:

Five Aurais MCP servers ("bots") — packages/journal-companion, market-scout, meeting-distiller, research-reader, writing-editor. Each is a standalone Model Context Protocol server (stdio by default) that calls Claude and emits a signed Aurais proof chain for every run.
One verifier — packages/proof-verifier → @vorionsys/aurais-verify, a no-network CLI that checks proof chains offline (Ed25519 signatures, hash links, sequence, key consistency).

All six depend on the published @vorionsys/aurais-core (^0.1.0) for the trust primitives: ProofChain, deriveAgentIdentity, canonicalJSON, sha256.

Layout

packages/
  journal-companion/  market-scout/  meeting-distiller/
  research-reader/    writing-editor/        # the 5 bots
  proof-verifier/                            # @vorionsys/aurais-verify

Per package: src/ (TypeScript) → dist/ (built, gitignored), test/*.test.mjs (node:test).

Commands

npm ci                                         # install
npm run typecheck --workspaces --if-present    # tsc --noEmit
npm run build     --workspaces --if-present    # tsc -> dist/
npm test          --workspaces --if-present    # node:test

Run a bot over stdio (needs an API key):

ANTHROPIC_API_KEY=… node packages/<bot>/dist/index.js

Conventions

Lock-step versioning — all six packages share one version; bump together.
Releases — tag-triggered OIDC trusted publishing (no tokens) plus an auto-created GitHub Release. See RELEASING.md.
Transports — stdio is the default. AURAIS_TRANSPORT=http enables a remote HTTP transport with a per-request X-Anthropic-Key; an opt-in OAuth 2.1 resource-server mode is available over HTTP. Both unset → no auth, stdio.
Provenance — every proof chain records package_version, read at runtime from the package's own package.json (never hardcoded).
Branching — develop on a feature branch, PR into main; the build-and-test CI check runs on PRs.

Read the full file on GitHub · 66 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 · 66 lines · 636 tokens per session scan A b28228c01275

Subscribe to this mod's changes

aurais-mcp-bots CLAUDE.md is an instructions file published in the GitHub repository vorionsys/aurais-mcp-bots (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 636 tokens to every session, about $0.0025 per session on Opus 5.5. 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.

aurais-mcp-bots CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aurais-mcp-bots CLAUDE.mdvorionsys/aurais-mcp-bots	Instructions file	1	3mo ago	Apache-2.0	A	636	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

aurais-mcp-bots: Instructions file for Claude Code