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/bitrefill/agents/claude-mdgit clone --depth 1 https://github.com/bitrefill/agentsWhat 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 | $0.00884 | $0.00884 |
| Opus 5 | $0.00442 | $0.00442 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
agents 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bitrefill Skills — Agent Guide
Instructions:
- Be semantically dense and token efficient. Prefer concise, information-rich responses; avoid filler, repetition, and unnecessary elaboration.
- Whene editing, never mention the previous version or the changes you made. All the contents must be authoritative and up to date.
- Try abstracting instructions that can be applied to multiple cases
- Avoid creating new sections as much as possible. Try updating exisiting knowledge instead.
This repository is a monorepo of agent skills for Bitrefill, packaged as a Claude Code / Cowork plugin marketplace. Skills live in the skills/ directory and are distributed through the plugin system shared by Claude Code and Claude Cowork.
Installing the Plugin
Claude Code
/plugin marketplace add bitrefill/agents
/plugin install bitrefill@bitrefill-skills
/reload-plugins
Bundled eCommerce MCP (.mcp.json, OAuth on first call). Pin: bitrefill/[email protected].
Claude Cowork
Customize → Plugins → add bitrefill/agents → install bitrefill.
claude.ai (Chat)
Connectors only → skills/bitrefill/references/harnesses/claude-chat.md.
Local Testing
claude --plugin-dir ./
/reload-plugins after edits. claude plugin validate . before publish.
Repository Structure
.claude-plugin/
plugin.json # Plugin manifest (name, version, author)
marketplace.json # Marketplace catalog listing the plugin
.mcp.json # Optional — MCP server definitions (eCommerce HTTP MCP for this repo)
skills/
<skill-name>/
SKILL.md # Required — frontmatter + agent instructions
references/ # Optional — supporting docs, examples
The marketplace (marketplace.json) lists plugins available for installation. The plugin manifest (plugin.json) defines the plugin's identity. Skills inside skills/ are auto-discovered when the plugin loads. MCP servers in .mcp.json start when the plugin is enabled.
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 · 95 lines · 884 tokens per session scan A b5622e61a7ec
agents CLAUDE.md is an instructions file published in the GitHub repository bitrefill/agents (22 stars, last pushed 2mo ago), licensed MIT. It adds 884 tokens to every session, about $0.0044 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
superpowers-zh CLAUDE.md
Instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
superpowers-zh GEMINI.md
Instructions for jnMetaCode/superpowers-zh, covering superpowers-zh 中文增强版, 核心规则, 可用 skills and 如何使用.
agent-skills GEMINI.md
Instructions for mongodb/agent-skills, covering mongodb gemini extension and configuration.
slack-skills-plugin AGENTS.md
Instructions for slackapi/slack-skills-plugin, covering slack plugin, commands, development commands, cross-skill references and skill descriptions.
ai-rules-sync AGENTS.md
Instructions for lbb00/ai-rules-sync, covering agents instructions, project overview, tech stack, key features and directory structure.
skill-buddy AGENTS.md
Instructions for konnga/skill-buddy, a project described as: AI Skills Buddy, A desktop workspace for managing, installing, and synchronizing Skills and MCP Servers across AI agents.