aura CLAUDE.md

aura CLAUDE.md is an instructions file for coding agents from Naridon-Inc/aura. It costs 2,105 tokens per session, scanned A, original, Apache-2.0.

Mandatory instructions for Aura, a semantic version-control system that tracks code structure rather than only changed lines. They require Claude Code to use Aura while working and to check the project's shared state first.

In plain words
What is it for?
Use them when changing code in the Aura-managed project. They cover checking status, pulling teammates' changes, reviewing affected code, and respecting locked safety settings.
Why use it?
They help detect risky code changes, accidental deletions, and pending work from teammates before new edits are made.

Instructions file

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.

agentmods
npx agentmods add instructions/naridon-inc/aura/claude-md
Clone the repo
git clone --depth 1 https://github.com/Naridon-Inc/aura

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 aura CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/naridon-inc/aura/claude-md.svg)](https://agentmods.dev/instructions/naridon-inc/aura/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/naridon-inc/aura/claude-md"><img src="https://agentmods.dev/badge/instructions/naridon-inc/aura/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,105 This file is loaded in full into every session.
When invoked 2,105 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02105 $0.02105
Opus 5 $0.01052 $0.01052
Sonnet 5 $0.00421 $0.00421
Haiku 4.5 $0.00211 $0.00211

Measured 5d ago against content hash a7961a557a28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aura 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 5d 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 · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AURA SEMANTIC ENGINE — MANDATORY PROTOCOL FOR CLAUDE CODE

You are Claude (Anthropic), running inside Claude Code CLI. Model: Claude Opus 4.6 / Sonnet 4.6 Aura Version: v0.12.6 MCP Server: aura-vcs (29+ tools available)

YOU MUST USE AURA. THIS IS NOT OPTIONAL.

Aura is a semantic version control engine that tracks your code changes at the AST level. It catches bugs you miss, prevents accidental deletions, and mathematically verifies your work. Every command below exists to protect the codebase from AI mistakes — including yours.


BEFORE WRITING ANY CODE

  1. Check semantic state — call aura_status MCP tool
    • Shows: logic nodes tracked, active session, checkpoints, strict mode
    • Shows: team sync status — mothership online/offline, pending pulls from teammates, peer count
    • If team.pending_pull exists: STOP and call aura_live_sync_pull first — your teammates pushed changes
    • If strict mode is ON, the pre-commit hook WILL block you if you delete functions without logging intent
    • If strict_mode_locked: true, you CANNOT disable strict mode — only a human with the passcode can

1.5. Check cross-branch impacts — call aura_live_impacts MCP tool

  • Shows unresolved impact alerts where functions you depend on were modified/deleted on other branches
  • Fix or acknowledge each alert, then call aura_live_resolve with the alert ID

1.6. Read team messages — if you see 💬 TEAM: N unread messages, call aura_msg_list immediately

  • Another developer or AI agent may be coordinating with you
  • Read the message and respond via aura_msg_send if needed
  • Do NOT ignore team messages — they may contain critical context about what others are changing
  1. Plan multi-file features — call aura_plan_discover MCP tool with your objective
    • Required when: task touches 3+ files, adds a new feature, or refactors existing architecture
    • Returns: gray areas (decisions needing human input) + atomic wave plan
    • Then call aura_plan_lock to lock decisions, aura_plan_next to get each wave

Read the full file on GitHub · 161 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. 5d ago First seen · 161 lines · 2,105 tokens per session scan A a7961a557a28

Subscribe to this mod's changes

aura CLAUDE.md is an instructions file published in the GitHub repository Naridon-Inc/aura (45 stars, last pushed 15d ago), licensed Apache-2.0. It adds 2,105 tokens to every session, about $0.0105 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.