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/ggwhite/4x/claude-mdgit clone --depth 1 https://github.com/ggwhite/4xWrote 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/ggwhite/4x/claude-md)<a href="https://agentmods.dev/instructions/ggwhite/4x/claude-md"><img src="https://agentmods.dev/badge/instructions/ggwhite/4x/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 | $0.01973 | $0.01973 |
| Opus 5 | $0.00986 | $0.00986 |
| Sonnet 5 | $0.00395 | $0.00395 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade A, and why
4x 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 4d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@.4x/plugins/CLAUDE.md
4x — Multi-Role AI Development Loop
Quick Start
make build # 編譯 CLI 至 bin/4x
make test # go test ./...
make lint # go vet + gofmt + golangci-lint
Architecture
三層架構，CLI 層不呼叫 LLM：
cmd/4x/ CLI entry point (Cobra)，每個 subcommand 一個檔案
internal/
protocol/ .4x/ 檔案格式、Workspace 讀寫、型別定義
state/ 狀態機（phase transition）
guard/ Guardrail 檢查（scope/baseline/required files）
orchestrator/ Run loop 核心編排邏輯
runner/ Runner 介面與子程序執行
batch/ Batch DAG 排程
feature/ Feature CRUD 操作
doctor/ 專案健康檢查
prompt/ Role prompt 模板渲染
gitops/ Git 操作（diff/worktree/changed files）
server/ SSE + REST server（Dashboard 用）
... （其餘：enrich, envutil, evolution, health, hook, learning, logging, mcp, schemasync, vcshub, verify）
plugins/
claude-code/ Claude Code runner instructions
gemini/ Gemini CLI runner instructions
codex/ Codex CLI runner instructions
agy/ Antigravity CLI runner instructions
copilot/ Copilot CLI runner instructions
cursor/ Cursor rules (.cursorrules)
opencode/ OpenCode runner instructions
embed.go go:embed 將 plugin 檔嵌入 binary
dashboard/
macos/ Swift native app
schemas/ JSON Schema（state/event/feature）
templates/ Role prompt templates（.md.tmpl）
docs/ 權威設計規格（見 docs/AGENTS.md 索引）
State Machine
init → designing → design-reviewing → coding → reviewing → testing → deep-reviewing → fixing ─┐
↑ ↓ ↑ ↓ ↓↺ ↓ ↓
↑ designing(FAIL) ↑ amending ←─────┴───────────┤ accepting
↑ ↑ ↓ ↓ ↓
└─────────────────────────────┴────────┴──────────────────────┘ pending-review
↓
done
any → blocked / needs-attention / done / abandoned（done 和 abandoned 為不可逆終態）
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.
- 4d ago First seen · 169 lines · 1,973 tokens per session scan A 540d005c8f18
4x CLAUDE.md is an instructions file published in the GitHub repository ggwhite/4x (33 stars, last pushed 9d ago), licensed MIT. It adds 1,973 tokens to every session, about $0.0099 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.