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.
npx agentmods add instructions/hbkdad/arc/claude-mdgit clone --depth 1 https://github.com/hbkdad/arcWrote 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.
[](https://agentmods.dev/instructions/hbkdad/arc/claude-md)<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>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 | $0.00508 | $0.00508 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
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.
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
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.
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.
- 3d ago First seen · 27 lines · 508 tokens per session scan A abf5c1af1b3c
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.
Other instructions, from other repositories
rizzo-pii CLAUDE.md
Instructions for Rizzo-AI-Academy/rizzo-pii, covering claude.md, cos'è questo progetto, ambiente — vincoli critici e non ovvi, mappa della repo and tassonomia: 22 tag (dettaglio in tassonomiatag.md).
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
openhuman CLAUDE.md
Claude Code instructions for tinyhumansai/openhuman, a project described as: Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
Vault-Agent-Memory AGENTS.md
Instructions for zycaskevin/Vault-Agent-Memory, covering agent instructions for vault agent memory, common install architecture, second decision: optional features, first decision: database scope and safe agent workflow.