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/agentsdance/agentx/claude-mdgit clone --depth 1 https://github.com/agentsdance/agentxWhat 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 | $0.00623 | $0.00623 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade B, and why
agentx CLAUDE.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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Codex: `~/.codex/config.toml` How it starts
The opening of the file, as written. The whole thing — 70 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.
Build and Run Commands
# Build the binary (injects version from git tags)
make build
# Run the TUI
./agentx
# Run CLI commands
./agentx install playwright
./agentx skills list
./agentx plugins list
# Run tests
go test ./...
# Run a single test
go test -run TestParseGitHubTreeURL ./internal/skills/
# Clean build artifacts
make clean
Git Operations
Never run git commit or git push - the user handles all git operations manually.
Architecture
AgentX is a CLI tool for managing MCP servers, skills, and plugins across multiple AI coding agents (Claude Code, Codex, Cursor, Gemini CLI, OpenCode).
Core Layers
CLI Layer (cmd/): Cobra-based commands. root.go launches the TUI when run without arguments, or delegates to subcommands (install, check, list, remove, skills, plugins).
Agent Abstraction (internal/agent/): The Agent interface defines operations for all supported agents. Each agent (Claude, Codex, Cursor, Gemini, OpenCode) implements this interface with its own config file location and format:
- Claude Code:
~/.claude.json - Codex:
~/.codex/config.toml - Cursor:
~/.cursor/mcp.json - Gemini CLI:
~/.gemini/settings.json - OpenCode:
~/.opencode/config.json
Domain Logic (internal/):
skills/: Skill installation from local paths or Git repos, YAML frontmatter parsingplugins/: Plugin management with remote registry fetch and local cachingconfig/: JSON config file reading/writing for agent configurationsmcp/: MCP server definitions (Playwright, Context7)
TUI Layer (ui/): Built with Bubble Tea and Lip Gloss.
app.go: Main model coordinating views, tabs, header, sidebar, and footerviews/: Four tab views (MCP, Skills, Plugins, Agents) - each implements the View interfacecomponents/: Reusable UI pieces (TabBar, Header, Sidebar, Footer)theme/: Color scheme and styling
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.
- 2d ago First seen · 70 lines · 623 tokens per session scan B 4b2ad80c9aad
agentx CLAUDE.md is an instructions file published in the GitHub repository agentsdance/agentx (51 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 623 tokens to every session, about $0.0031 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
clean-code-skills clean-code.instructions.md
Instructions for btseee/clean-code-skills, covering clean-code instructions, clean code rules (clean-code-skills), work loop, dependency direction and file and code placement.
claude-skills-management CLAUDE.md
Instructions for hardness1020/claude-skills-management, covering claude.md, plugin release, plugin update and python.
scoop-skills AGENTS.md
AGENTS.md instructions for entr0pia/scoop-skills, covering scoop skills 项目概述, 仓库概述, 项目结构, 技能说明 and scoop-skills.
scoop-skills GEMINI.md
Gemini CLI instructions for entr0pia/scoop-skills, covering scoop skills 项目概述, 仓库概述, 项目结构, 技能说明 and scoop-skills.
skills CLAUDE.md
Instructions for Foysal50x/skills, a project described as: Opinionated Laravel engineering skills for AI coding agents.
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).