agentmods.dev

ARC CLAUDE.md

Repository instructions for ARC, a command-line and terminal interface for managing multiple AI coding-agent profiles. Profiles keep settings, credentials, and environments separate.

In plain words
What is it for?
Building or modifying ARC features such as profiles, sessions, tasks, skills, settings, synchronization, telemetry, and troubleshooting screens.
Why use it?
They explain the project’s architecture and conventions so changes fit its command interface, terminal screens, setup flow, and repair tools.

Instructions file

3 2mo ago A scan 1,211 tokens original MIT
View the source file Codename-11/ARC
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/codename-11/arc/claude-md
Clone the repo
git clone --depth 1 https://github.com/Codename-11/ARC
Per session 1,211 This file is loaded in full into every session.
When invoked 1,211 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 $0.01211 $0.01211
Opus 5 $0.00606 $0.00606
Sonnet 5 $0.00242 $0.00242
Haiku 4.5 $0.00121 $0.00121

Measured 2d ago against content hash 7add82f6b7f6, 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 2d 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 · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — ARC Project

What is ARC?

ARC (Agent Runtime Control) is a CLI + TUI for managing multiple agent profiles (Claude Code, Gemini CLI, Codex CLI, etc.) with isolated configs, credentials, and environments.

Architecture

  • CLI layer: Commander.js commands in src/commands/
  • TUI layer: Ink + React components in src/tui/
    • Views: Dash, Work (session), Profiles, Doctor, Settings, Guide (in-app docs), Tasks, Memory, Skills, Sync, Telemetry (Traces), Agents
    • Overlays: CreateProfileOverlay, HelpOverlay, CommandPalette, SwapOverlay, SharedDetailOverlay, ProfileInfoOverlay, Update overlay
    • OnboardingScreen: fullscreen first-run wizard with multi-select tool import, optional rename, batch import
    • Workspace shell: tokenized input with syntax highlighting (/command green, @profile blue, #tag dimmed) and auto-complete overlay (Tab/Enter accept, arrows navigate); runs shell commands with profile env; / commands for ARC actions
    • Input components: TokenizedInput (tokenizer + colored rendering), AutoComplete (suggestion resolver + overlay)
    • Doctor repair actions: install hints, re-auth instructions, PATH/shell fix hints displayed inline
    • Shared layer controls: h key in ProfilesView toggles shared layer per profile; sync status in SettingsView and ProfileList
    • Credential hot-swap: SwapOverlay (src/tui/views/SwapOverlay.tsx) — capture/swap/delete via command palette. [experimental]
    • Update system: DashView shows update-available banner; u key triggers in-app update overlay
    • Scrollable views: ScrollBox component (src/tui/components/ScrollBox.tsx) for arrow-key scrolling
  • Update module: src/update.ts — cached npm registry check, self-update via npm install -g
  • Credential hot-swap: src/swap.ts — [experimental] swap auth credentials in canonical tool dir without changing MCPs/settings/history. CLI: arc swap capture/to/list/delete. TUI: SwapOverlay via command palette
  • Shared layer: src/shared.ts — syncs MCP servers, commands, CLAUDE.md, memory, and projects across profiles via ~/.arc/shared/. Pull/push with cross-tool warnings.
  • Import utilities: src/import-utils.ts — shared skip list, auth detection, entry descriptions
  • Wizard types: src/tui/wizardTypes.ts — shared step types and metadata helpers for profile creation wizards
  • Activity log: src/log.ts — timestamped action log to ~/.arc/activity.log
  • Single entry point: src/index.ts → src/cli.ts
  • Bundled output: tsup produces a single dist/index.js with shebang
  • Landing site: site/ — React 19 + Vite + Tailwind v4, Nothing-design marketing page
  • Deployment: Root Dockerfile + nginx.conf — multi-stage build merging site/ at / and user-docs/ at /docs/ into single nginx container
  • Web Dashboard: 13 view components (Overview, Sessions, Traces, Risk, Tasks, Skills, Memory, Agents, Factory + Profiles, Diagnostics, Sync, Plugins)
  • Orchestration layer: Hook pipeline (8 hooks in priority order), roundtable multi-agent discussions, task delegation protocol, interagent routing, source classification
  • Adapters: Claude Code (SDK + plugin + hooks), Codex CLI, Gemini CLI, OpenClaw (native plugin), Hermes Agent (MCP bridge), Generic (fallback for any tool)

Read the full file on GitHub · 74 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. 2d ago First seen · 74 lines · 1,211 tokens per session scan A 7add82f6b7f6

Subscribe to this mod's changes

ARC CLAUDE.md is an instructions file published in the GitHub repository Codename-11/ARC (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,211 tokens to every session, about $0.0061 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.

Analytics and metricsDebuggingPlanningagent-managementai-agentsclaude-codeclicodex-clideveloper-tools
Related

Other instructions, from other repositories

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens

amfs CLAUDE.md

Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.

raia-live/amfs · 2,185 tokens

CodexPotter AGENTS.md

Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.

breezewish/CodexPotter · 306 tokens

copilot-proxy-api CLAUDE.md

Instructions for voidsteed/copilot-proxy-api, covering claude.md, project overview, common commands, architecture and entry points & cli structure.

voidsteed/copilot-proxy-api · 3,899 tokens

OpenMicro AGENTS.md

Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.

stephenleo/OpenMicro · 123 tokens

squarebox CLAUDE.md

Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.

SquareWaveSystems/squarebox · 1,772 tokens