normsync CLAUDE.md

normsync CLAUDE.md is an instructions file for coding agents from sandeep-alluru/normsync. It costs 248 tokens per session, scanned A, original, MIT.

Project instructions for normsync, a planned system for enforcing shared rules between multiple AI-controlled characters or agents.

In plain words
What is it for?
Use them when designing the signed shared-rule ledger, agent commands, deterministic enforcement engine, demo, and Python package API.
Why use it?
They record the intended architecture, decisions, current status, and minimum viable product so implementation work follows a consistent design.

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/sandeep-alluru/normsync/claude-md
Clone the repo
git clone --depth 1 https://github.com/sandeep-alluru/normsync

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 normsync CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandeep-alluru/normsync/claude-md.svg)](https://agentmods.dev/instructions/sandeep-alluru/normsync/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sandeep-alluru/normsync/claude-md"><img src="https://agentmods.dev/badge/instructions/sandeep-alluru/normsync/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 248 This file is loaded in full into every session.
When invoked 248 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 $0.00248 $0.00248
Opus 5 $0.00124 $0.00124
Sonnet 5 $0.00050 $0.00050
Haiku 4.5 $0.00025 $0.00025

Measured 3d ago against content hash aa5a4fba0884, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

normsync 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 3d 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 · 23 lines

What it actually says

normsync — Session Anchor

Research spec: ../tech-research/14-Gaming/social-contract-enforcement-engine-binding-multi-agent-n/README.md
One-liner: Emergent norm enforcement for multi-agent worlds — signed CRDT commitment ledger
Phase: backlog
Stack: Python, automerge-py (or py-crdt), cryptography, anthropic (Claude API)

Key decisions

  • Key architectural separation: LLM decides WHAT norms exist; deterministic engine decides enforcement

Next step

Read the research spec, then design the signed commitment ledger schema.

MVP definition

  • pip install normsync works
  • Signed, versioned, append-only CRDT commitment ledger
  • Tool-call interface: agents propose norms, accept norms, query active norms
  • Deterministic enforcement engine (no LLM in the enforcement path)
  • Demo: two NPC agents negotiate "don't attack allies" norm; third agent violates it; enforcement fires
  • API: normsync.propose(norm), normsync.accept(norm_id), normsync.enforce(action)
  • README with clear architecture diagram showing LLM vs deterministic boundary
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. 3d ago First seen · 23 lines · 248 tokens per session scan A aa5a4fba0884

Subscribe to this mod's changes

normsync CLAUDE.md is an instructions file published in the GitHub repository sandeep-alluru/normsync (0 stars, last pushed 17d ago), licensed MIT. It adds 248 tokens to every session, about $0.0012 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 instructions, from other repositories