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/nyatinte/ccexp/agents-mdgit clone --depth 1 https://github.com/nyatinte/ccexpWrote 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/nyatinte/ccexp/agents-md)<a href="https://agentmods.dev/instructions/nyatinte/ccexp/agents-md"><img src="https://agentmods.dev/badge/instructions/nyatinte/ccexp/agents-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 | $0.03803 | $0.03803 |
| Opus 5 | $0.01902 | $0.01902 |
| Sonnet 5 | $0.00761 | $0.00761 |
| Haiku 4.5 | $0.00380 | $0.00380 |
Grade B, and why
ccexp AGENTS.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **~/.claude/settings.json** → User settings (global) How it starts
The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
ccexp (short for claude-code-explorer) - React Ink-based CLI tool for exploring and managing Claude Code settings and slash commands. The tool provides an interactive terminal UI for file navigation, content preview, and file management operations. The package was renamed from claude-code-explorer to ccexp for brevity and easier command-line usage.
Core Commands
# Development
bun run start # Run CLI in development mode
bun run build # Build for production (outputs to dist/)
bun run typecheck # TypeScript type checking
# Testing (InSource Testing Pattern)
bun run test # Run all tests
bun run test:watch # Test in watch mode
bun run test src/_utils.ts # Run tests for specific file
# Quality Management
bun run check # Biome lint/format check
bun run check:write # Biome auto-fix
bun run check:unsafe # Biome unsafe auto-fix
bun run knip # Check for unused dependencies/exports
bun run ci # Full CI pipeline (build + check + typecheck + knip + test)
# Release Management
bun run release # Interactive version bumping with bumpp
bun run prepack # Pre-publish build and package.json cleanup
# CLI Usage
./dist/index.js # Interactive React Ink TUI mode
bun run start # Development mode with hot reload
bun run dev # Development mode with watch
Technical Architecture
Main Tech Stack
- Runtime: Bun + Node.js (>= 20) - ESM only
- React TUI Framework: React Ink (v6) for terminal UI components
- UI Components: @inkjs/ui for enhanced terminal components (TextInput, Spinner, StatusMessage)
- Build: tsdown (Rolldown/Oxc) → produces shebang executable with type definitions
- Configured in
tsdown.config.tsfor ESM-only output - Automatic shebang injection for CLI usage
- Type definition generation with
dts: true
- Configured in
- Testing: vitest (InSource Testing + globals) + ink-testing-library
- Linting: Biome (v2.0.6) with strict rules
- Dependency Management: knip for unused dependency detection
- File Operations: fdir for fast directory scanning + node:fs/promises
- Pattern Matching: ts-pattern for complex conditional logic
- Validation: zod + branded types for runtime type safety
- System Integration: open, clipboardy for file operations
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 · 454 lines · 3,803 tokens per session scan B 184e0227f8f0
ccexp AGENTS.md is an instructions file published in the GitHub repository nyatinte/ccexp (271 stars, last pushed 9d ago), licensed MIT. It adds 3,803 tokens to every session, about $0.0190 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.