Arcgentic: Instructions file for Claude Code

CLAUDE.md

Arcgentic CLAUDE.md is an instructions file for Claude Code from Arch1eSUN/Arcgentic. It costs 6,622 tokens per session, scanned A, original, MIT.

A development handoff for Arcgentic, describing the current milestone, required specifications, repository layout, and files planned for the next release. It is automatically read by Claude Code at the start of a session.

In plain words
What is it for?
Use it when continuing Arcgentic development, reading the required release specification, locating the Python toolkit, or implementing the listed milestone files.
Why use it?
It gives a continuing coding session the project's current state and authoritative instructions before implementation begins.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the TodoWrite tool.

This is Arch1eSUN/Arcgentic's own configuration. It tells Claude Code how to work on Arcgentic itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Arcgentic configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/archiesun/Desktop/Arc.

Reuse

Borrowing it

Nothing to install: this file belongs to Arch1eSUN/Arcgentic. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Arch1eSUN/Arcgentic/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic

Made for: Claude Code.

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 Arcgentic CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arch1esun/arcgentic/claude-md.svg)](https://agentmods.dev/instructions/arch1esun/arcgentic/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/arch1esun/arcgentic/claude-md"><img src="https://agentmods.dev/badge/instructions/arch1esun/arcgentic/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,622 This file is loaded in full into every session.
When invoked 6,622 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 5.1 $0.06622 $0.06622
Opus 5 $0.03311 $0.03311
Sonnet 5 $0.01324 $0.01324
Haiku 4.5 $0.00662 $0.00662

Measured 6d ago against content hash 892d16e0fe70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Arcgentic 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 6d 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 · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arcgentic v0.2.0 — Dev Session Handoff

This file is auto-loaded by Claude Code at session start. Read fully before any action. This is your single source of orientation for executing arcgentic v0.2.0.


1. Identity

You are a dev session continuing arcgentic development.

  • Previous milestone: v0.1.0-alpha.2 MVP, tagged @ 2efea61 on main, fully pushed to origin/main. See CLAUDE-v0.1.0-handoff.md for that session's context (archived).
  • Current milestone: v0.2.0 — full role coverage (the P0 group in spec § 19.3 three-phase split).
  • Build contract for this session: docs/plans/2026-05-13-arcgentic-v0.2.0-spec.md (3366 LOC / 23 sections, self-contained — read in full before Task 1).
  • ⚠ Spec Amendment 01 — AUTHORITATIVE (overrides spec § 18 / § 21.5 / § 22 directory paths): docs/plans/2026-05-13-arcgentic-v0.2.0-spec-amendment-01-layout.md. Read this BEFORE spec § 18. Founder ratified the cascade-spec-bug fix on 2026-05-13: hybrid monorepo — markdown skills/agents at repo root (v0.1 plugin contract preserved); Python toolkit at toolkit/src/arcgentic/ (PyPI-publishable CLI); markdown skills shell out to arcgentic CLI.

You execute the spec end-to-end for the P0 release only (v0.2.0 release; ~18h estimated). P1 (v0.2.1) and P2 (v0.2.2) are out of scope for this session.


2. NOT-this (boundary)

Boundary Why it matters
NOT Moirai (~/Desktop/Arc Studio/Moirai/) arcgentic is a separate plugin. Do not touch Moirai files. Do not commit to Moirai repo. (Spec § 23 cites Moirai as origin — that does NOT grant write access.)
NOT v0.1.0-alpha.2 rebuild v0.1.0 is closed. Tag v0.1.0-alpha.2 @ 2efea61 is published. Do not rewrite v0.1.0 history; do not amend any commit prior to HEAD-of-this-session.
NOT v0.2.1 (P1) work Per spec § 19.3: P1 = codify-lesson skill + track-refs skill + lesson-codifier + ref-tracker agents. These ship in v0.2.1, NOT v0.2.0.
NOT v0.2.2 (P2) work Per spec § 19.3: P2 = cross-session-handoff skill. Ships in v0.2.2.
NOT a planner role Spec is already a plan-level document (more detailed than v0.1.0's plan). Your job is execution, not plan-writing. If you find a spec gap → surface to founder; do NOT silently expand.
NOT an auditor role External audit happens after v0.2.0 ships. This session executes only.
NOT IDE adapter beyond spec § 3 Spec § 3 defines IDEAdapter Protocol + 4 implementations. Do not invent new adapters for Cursor variants / JetBrains / etc. — that's v0.3+ scope.

Read the full file on GitHub · 408 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. 6d ago First seen · 408 lines · 6,622 tokens per session scan A 892d16e0fe70

Subscribe to this mod's changes

Arcgentic CLAUDE.md is an instructions file published in the GitHub repository Arch1eSUN/Arcgentic (292 stars, last pushed 24d ago), licensed MIT. It adds 6,622 tokens to every session, about $0.0331 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens