arc CLAUDE.md

arc CLAUDE.md is an instructions file for coding agents from hbkdad/arc. It costs 508 tokens per session, scanned A, original, MIT.

Repository instructions for building ACR, a local-first system that coordinates AI models and roles. They require the coding agent to read the project’s master instructions, implement only the next milestone, run tests, and write a session report.

In plain words
What is it for?
Use them at the start and end of implementation sessions in this repository, especially when working in its modular monorepo, which contains multiple related applications and packages.
Why use it?
They set strict limits and required checks so development stays focused, secure, and verifiable.

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/hbkdad/arc/claude-md
Clone the repo
git clone --depth 1 https://github.com/hbkdad/arc

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 arc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hbkdad/arc/claude-md.svg)](https://agentmods.dev/instructions/hbkdad/arc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hbkdad/arc/claude-md"><img src="https://agentmods.dev/badge/instructions/hbkdad/arc/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 508 This file is loaded in full into every session.
When invoked 508 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 $0.00508 $0.00508
Opus 5 $0.00254 $0.00254
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 3d ago against content hash abf5c1af1b3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arc 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 · 27 lines

How it starts

The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repo builds ACR — Adaptive Cognitive Runtime, a local-first, model-independent AI orchestration runtime.

Full specification (roles, principles, architecture, milestones, security model, required report format): → ACR_MASTER_SYSTEM_PROMPT.md

Read it in full before any implementation work. Do not ask for a summary in place of reading it.

Start every session with

SESSION_TASK_PROMPT.md

Non-negotiables (see master file for full list)

  • Only build the next incomplete milestone (master §65–66). One smallest-complete vertical slice at a time — never the whole system in one session.
  • Never rewrite unrelated modules, remove working behavior without justification, or claim a feature works without running its tests.
  • Minimal context: don't load the whole repo, whole README, or full history into a task — retrieve only what's relevant (master §7–8).
  • Default deny on permissions; no secrets in code, logs, memory, or Git (master §37–41).
  • End every session with the Required Session Report (master §73): STATUS, IMPLEMENTED, FILES CHANGED, TESTS, TOKEN OPTIMIZATION, SECURITY, DECISIONS, NEXT STEP.

Repo layout

Modular monorepo (master §5): apps/, packages/, core/, memory/, context/, skills/, agents/, routing/, providers/, tools/, learning/, telemetry/, security/, benchmarks/, migrations/, tests/, scripts/, examples/, docs/. Core domain logic must not depend on UI, provider implementations, or deployment platforms.

Today this lives as one src/acr/ package with each domain as a submodule (acr.memory, acr.agents, ...) rather than literal top-level directories — a deliberate, revisit-when-needed choice, not drift; see docs/adr/0001-src-layout-single-package.md. The dependency-direction rule still applies at the submodule level: nothing under acr.core/acr.memory/etc. may import a concrete provider adapter or acr.dashboard/acr.cli — only acr.providers.base's abstract interface.

Read the full file on GitHub · 27 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. 3d ago First seen · 27 lines · 508 tokens per session scan A abf5c1af1b3c

Subscribe to this mod's changes

arc CLAUDE.md is an instructions file published in the GitHub repository hbkdad/arc (4 stars, last pushed 1mo ago), licensed MIT. It adds 508 tokens to every session, about $0.0025 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