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/basaltbytes/agentic-tools/claude-mdgit clone --depth 1 https://github.com/basaltbytes/agentic-toolsWhat 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 | $0.02140 | $0.02140 |
| Opus 5 | $0.01070 | $0.01070 |
| Sonnet 5 | $0.00428 | $0.00428 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
agentic-tools 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 yesterday.
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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Basaltbytes Agentic Tools - Project Context for AI Assistants
Project Overview
This repository is a collection of agentic tools - AI-powered development automation workflows that can be deployed across multiple platforms. Currently supports Claude Code as the primary deployment target, with architecture designed for multi-platform expansion.
Repository: basaltbytes/agentic-tools
Organization: Basaltbytes
Contact: [email protected]
Repository Philosophy
Multi-Platform Ready: Tools are designed to be platform-agnostic in concept, with implementations for specific platforms. Currently focused on Claude Code, with architecture that can support future platforms.
Current Deployment Targets:
- Claude Code (via marketplace/plugin system)
- Future: Cursor, Windsurf, custom CLIs, etc.
Repository Structure
agentic-tools/
├── .claude-plugin/ # Claude Code marketplace configuration
│ └── marketplace.json # Lists all available Claude Code plugins
│
├── {tool-name}-plugin/ # Claude Code implementation of a tool
│ ├── .claude-plugin/
│ │ └── plugin.json # Claude Code plugin manifest
│ ├── commands/
│ │ └── {command}.md # Command definitions with frontmatter
│ └── README.md # Tool documentation
│
├── README.md # User-facing repository overview
├── CONTRIBUTING.md # Contribution guidelines
├── CLAUDE.md # This file - context for AI assistants
└── LICENSE # MIT license
Current Tools
i18next-translate
- Location:
./i18next-translate-plugin/ - Command:
/translate - Purpose: Automates finding and fixing hardcoded strings in i18next projects with self-verification loop
- Category: development-automation
How Claude Code Marketplace Works
Installation by Users
- Users add the marketplace once:
/plugin marketplace add basaltbytes/agentic-tools
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.
- yesterday First seen · 325 lines · 2,140 tokens per session scan A dd36e0a31dc4
agentic-tools CLAUDE.md is an instructions file published in the GitHub repository basaltbytes/agentic-tools (2 stars, last pushed 7mo ago), licensed MIT. It adds 2,140 tokens to every session, about $0.0107 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 2026-08-31.
Other instructions, from other repositories
learn-anything CLAUDE.md
Instructions for ChenChenyaqi/learn-anything, covering claude.md, project overview, commands, per-package commands and architecture (monorepo).
mattpocock-skills-zh CLAUDE.md
Instructions for devcxl/mattpocock-skills-zh, a project described as: Matt Pocock 技能集的中文翻译版 — 地道中文，原汁原味的技术术语。基于 mattpocock/skills 复刻。每日中午12点钟同步.
myace AGENTS.md
AGENTS.md instructions for niels-emmer/myace, covering myace — ai agent maintenance guidelines, what this is, commands, backend (from backend/) and frontend (from frontend/).
ai-agent-playbook AGENTS.md
Instructions for jukrap/ai-agent-playbook, covering agents.md, working rules, skill structure and verification.
superpowers-zh AGENTS.md
Instructions for jnMetaCode/superpowers-zh, a project described as: 🦸 AI 编程超能力 · 中文增强版 — superpowers（116k+ ⭐）完整汉化 + 6 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI 等 16 款 AI 编程工具真正会干活.
plan-swarm AGENTS.md
Instructions for alexio777/plan-swarm: This repo is a skills package. When editing.