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/okx/plugin-store/claude-mdgit clone --depth 1 https://github.com/okx/plugin-storeWhat 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 | $0.00815 | $0.00815 |
| Opus 5 | $0.00407 | $0.00407 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
plugin-store 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 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.
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 — 74 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.
Project Overview
Plugin Store — a CLI marketplace for installing/uninstalling/updating Skills and MCP servers across Claude Code, Cursor, and OpenClaw.
Build & Test
cargo build # Debug build
cargo build --release # Release build
cargo test # Run all tests
cargo test <test_name> # Run a single test
cargo test --test integration_test # Run only integration tests
Architecture
Data Flow
Registry (GitHub JSON) → Cache (/.plugin-store/cache/) → Plugin selection → Agent detection → Component installation (skill/mcp/binary) → State tracking (/.plugin-store/installed.json)
Plugin Model
Each plugin (registry::models::Plugin) has three optional components:
- Skill — a SKILL.md file downloaded from a GitHub repo, written into the agent's skill directory
- MCP — an MCP server config (npm/pip/binary) injected into the agent's settings JSON
- Binary — a platform-specific binary downloaded from GitHub releases with optional checksum verification
Agent Adapter Pattern
agent::AgentAdapter trait defines how plugins integrate with each supported agent. Each adapter (claude_code, cursor, openclaw) implements detection, skill directory resolution, and MCP config read/write for its agent's config format. detect_agents() probes all adapters and returns which are available.
State Tracking
state::InstalledState persists to ~/.plugin-store/installed.json. Each installed plugin records which agents it was installed to, with per-agent paths (skill_path, mcp_key, binary_path) for clean uninstall.
CLI Dispatch
main.rs uses clap derive to parse commands → dispatches to commands::<name>::execute(). Each command handler orchestrates registry fetching, user interaction (via dialoguer), and installer calls. The install command supports --skill-only, --mcp-only, and --agent flags to skip interactive selection.
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 · 74 lines · 815 tokens per session scan A be32369f53c8
plugin-store CLAUDE.md is an instructions file published in the GitHub repository okx/plugin-store (11 stars, last pushed 29d ago), licensed MIT. It adds 815 tokens to every session, about $0.0041 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.