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/icebear0828/clio/claude-mdgit clone --depth 1 https://github.com/icebear0828/clioWrote 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/icebear0828/clio/claude-md)<a href="https://agentmods.dev/instructions/icebear0828/clio/claude-md"><img src="https://agentmods.dev/badge/instructions/icebear0828/clio/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 5.1 | $0.02384 | $0.02384 |
| Opus 5 | $0.01192 | $0.01192 |
| Sonnet 5 | $0.00477 | $0.00477 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
clio 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.
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.
Clio — Claude Code CLI Clone
Agentic coding CLI that connects to Anthropic API (or compatible endpoints) to provide a terminal-based Claude Code experience. 47 source files, ~9.7k lines, single runtime dependency (fast-glob).
Quick Reference
npm run dev # Run without build (tsx)
npm run build # Compile TypeScript
npm run test # Run all tests (vitest)
npm run test -- --watch # Watch mode
npm run test -- tests/permissions.test.ts # Single file
Architecture
src/
├── index.ts # Entry: REPL loop, command routing, print mode (-p)
├── types.ts # Shared types (Config, Message, ContentBlock, UsageStats)
├── core/ # Engine (18 files)
│ ├── agent.ts # Agent loop (25 max iterations, auto-compact at 85%)
│ ├── client.ts # HTTP client (SSE streaming, retry 429/502/503/504)
│ ├── system-prompt.ts # 14-section system prompt builder
│ ├── section-cache.ts # Static sections cached per session, dynamic recomputed
│ ├── context.ts # CLAUDE.md upward traversal + git context
│ ├── settings.ts # 4-layer config merge (global → project × committed/local)
│ ├── permissions.ts # 3 modes (default/auto/plan) + allow/deny rules
│ ├── llm-classifier.ts # 2-stage: pattern match → LLM fallback
│ ├── session.ts # Session persistence (~/.clio/sessions/)
│ ├── compact.ts # Context compaction via summarization
│ ├── normalize.ts # Message normalization (tool pairing, thinking blocks)
│ ├── memory.ts # Auto memory (4 types, MEMORY.md index)
│ ├── adaptive-thinking.ts # Dynamic thinking budget
│ ├── pricing.ts # Model pricing tables
│ ├── sandbox.ts # Path/network/env sandboxing
│ ├── billing.ts # Billing header for CC compatibility
│ └── prompts.ts # Prompt templates
├── tools/ # Tool system (9 files)
│ ├── index.ts # 21 tool definitions + executeTool() dispatcher
│ ├── mcp.ts # MCP server lifecycle (JSON-RPC 2.0, zero deps)
│ ├── lsp.ts # LSP client (Content-Length framing, zero deps)
│ ├── subagent.ts # Sub-agent spawning (foreground/background/worktree)
│ ├── teams.ts # Agent team coordination + SendMessage
│ ├── hooks.ts # Pre/post tool hooks (shell commands)
│ ├── tasks.ts # In-memory task store
│ ├── checkpoint.ts # File undo/rollback
│ └── worktree.ts # Git worktree isolation
├── ui/ # Terminal UI (8 files)
│ ├── render.ts # ANSI colors, spinners, box drawing
│ ├── input.ts # Raw stdin, CSI parsing, undo/redo, history
│ ├── markdown.ts # Streaming markdown renderer
│ ├── highlight.ts # Syntax highlighting (TS/JS/Python/Rust/Go/Bash/JSON/CSS/HTML)
│ ├── statusbar.ts # Footer bar (model, tokens, cost)
│ ├── keybindings.ts # Keyboard shortcuts
│ ├── image.ts # Image detection + base64 encoding
│ └── file-completions.ts # @file tab completion
├── commands/ # Slash commands (4 files)
│ ├── git-commands.ts # /commit /pr /review
│ ├── init.ts # /init (generate CLAUDE.md)
│ ├── doctor.ts # /doctor (diagnostics)
│ └── custom-agents.ts # Agent definition loading (.md files)
├── plugins/ # Plugin system (4 files)
│ ├── types.ts, manifest.ts, loader.ts, index.ts
└── skills/ # Skills system (3 files)
├── index.ts, loader.ts, builtins/index.ts
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.
- 6d ago First seen · 169 lines · 2,384 tokens per session scan A c0044ff514e4
clio CLAUDE.md is an instructions file published in the GitHub repository icebear0828/clio (183 stars, last pushed 5mo ago), licensed MIT. It adds 2,384 tokens to every session, about $0.0119 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.
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.
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.
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).
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.