arc-1 AGENTS.md

arc-1 AGENTS.md is an instructions file for Codex, OpenCode from arc-mcp/arc-1. It costs 12,282 tokens per session, scanned A, original, MIT.

Project guidance for ARC-1, a TypeScript MCP server that lets Claude and other MCP clients work with SAP ABAP Development Tools. SAP ABAP is the programming environment used to build SAP business software.

In plain words
What is it for?
Use it when developing or deploying ARC-1, including its SAP read, search, write, activation, transport, Git, linting, diagnosis, and administration tools.
Why use it?
It explains the project's safety controls, identity handling, build and test process, and deployment rules for SAP operations.

Instructions file for CodexOpenCode

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

Made for: Codex, OpenCode.

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-1 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arc-mcp/arc-1/agents-md.svg)](https://agentmods.dev/instructions/arc-mcp/arc-1/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arc-mcp/arc-1/agents-md"><img src="https://agentmods.dev/badge/instructions/arc-mcp/arc-1/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 12,282 This file is loaded in full into every session.
When invoked 12,282 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 $0.12282 $0.12282
Opus 5 $0.06141 $0.06141
Sonnet 5 $0.02456 $0.02456
Haiku 4.5 $0.01228 $0.01228

Measured 3d ago against content hash fef0a5917764, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arc-1 AGENTS.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.

AGENTS.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Claude Code, Codex, Cursor, Copilot, …) working in this repository. Single source of truth — CLAUDE.md imports this file. Keep it terse: task→files + ≤1 gotcha per row; verbose details and live-verified behaviors live in docs/dev-guide.md (not auto-loaded — read the matching row there when working on one of these tasks).

Project Overview

ARC-1 is a TypeScript MCP (Model Context Protocol) server for SAP ABAP Development Tools (ADT). It provides 12 intent-based tools (SAPRead, SAPSearch, SAPWrite, SAPActivate, SAPNavigate, SAPQuery, SAPTransport, SAPGit, SAPContext, SAPLint, SAPDiagnose, SAPManage) for Claude and other MCP clients. Distributed as npm package (arc-1) and Docker image (ghcr.io/arc-mcp/arc-1).

Design Principles

  1. Centralized admin control — managed service; server-wide safety ceiling (allowWrites, package allowlists, SQL/data/transport/Git gates, deny actions); every call audited; per-user scopes restrict, never expand.
  2. Per-user SAP identity by default — principal propagation maps each MCP user to their own SAP user. ADR-0007 permits only an explicit mutation-free multi-target Basic exception, labeled shared and never used as PP fallback.
  3. Token-efficient tools — 12 intent tools vs 200+ endpoints, with schema payload guarded by CI budgets; hyperfocused mode = 1 tool (~200 tokens); method-level surgery + context compression keep mid-tier LLMs viable.
  4. BTP-native deployment — Destination Service, Cloud Connector, XSUAA OAuth, BTP Audit Log; also Docker/npm/stdio.
  5. Multi-client, vendor-neutral — XSUAA OAuth + Entra ID OIDC + API key coexist; one instance serves Claude, Copilot Studio, VS Code, Gemini CLI, Cursor.
  6. Safe defaults, opt-in power — read-only by default; free SQL blocked; package allowlist defaults to $TMP; everything forbidden until the admin allows it.
  7. Single target by default; one experimental read-only BTP exception — ADR-0005 remains the rule for writable/general multi-system access. ADR-0006 permits only the default-off BTP CF mode with explicit pinned/aggregate targets under its mutation-free safety contract. ADR-0007 permits the default-off shared Basic identity only under its one-instance/lockout controls. Do not broaden either exception to writes or another discovery/auth model without a new ADR/security review.

Read the full file on GitHub · 368 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 Changed · +4 lines · +91 tokens per session fef0a5917764
  2. 4d ago First seen · 364 lines · 12,191 tokens per session scan A cdbc061a05ee

Subscribe to this mod's changes

arc-1 AGENTS.md is an instructions file published in the GitHub repository arc-mcp/arc-1 (174 stars, last pushed 3d ago), licensed MIT. It adds 12,282 tokens to every session, about $0.0614 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.

Related

Other instructions, from other repositories

vscode accessibility.instructions.md

Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.

microsoft/vscode · 611 tokens

vscode design-philosophy.instructions.md

VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.

microsoft/vscode · 577 tokens

deepagents AGENTS.md

AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.

langchain-ai/deepagents · 2,268 tokens

ui-components AGENTS.md

AGENTS.md instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).

starc007/ui-components · 6,559 tokens

windmill AGENTS.md

AGENTS.md instructions for windmill-labs/windmill, covering windmill, workflow, documentation, dev environment and per-worktree ports and database.

windmill-labs/windmill · 4,072 tokens

walkerOS CLAUDE.md

Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.

elbwalker/walkerOS · 93 tokens