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/shopwarelabs/ai-coding-tools/agents-mdgit clone --depth 1 https://github.com/shopwareLabs/ai-coding-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 | $0.02669 | $0.02669 |
| Opus 5 | $0.01334 | $0.01334 |
| Sonnet 5 | $0.00534 | $0.00534 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade A, and why
ai-coding-tools AGENTS.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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@README.md
Shopware AI Coding Tools Marketplace - Technical Reference
Understanding Skills
Skills are executable code, not documentation. Markdown files in skills/[skill-name]/ directories (SKILL.md, references/*.md) are instruction files that Claude Code reads and executes. Modifying these files changes the skill's behavior directly - treat them as you would Python or JavaScript code.
Understanding Slash Commands
Slash commands are executable code, not documentation. Markdown files in commands/ directories are instruction files that Claude Code reads and executes when users invoke the command. Modifying these files changes what happens when users run the slash command.
Understanding Developer Documentation
AGENTS.md, README.md, and CHANGELOG.md inside plugins are developer documentation, not runtime code. These files are read by humans maintaining this repository. Claude Code does not load or execute them when the plugin is installed. Changes to these files affect documentation only, not plugin behavior.
Runtime files (executed by Claude Code):
skills/*/SKILL.mdandskills/*/references/*.mdagents/*.mdcommands/*.mdhooks/(hooks.json and scripts).mcp.json
When modifying runtime behavior (e.g. MCP tool references, workflow instructions), edit only runtime files. When updating architectural descriptions or usage guides, edit the developer documentation.
Marketplace Architecture
This marketplace uses a distributed metadata pattern where plugin metadata is stored in individual plugin.json files rather than centralized in marketplace.json.
Structure
.claude-plugin/marketplace.json # Minimal registry (name + source only)
plugins/
[category]/
[plugin-name]/
.claude-plugin/plugin.json # Full plugin metadata
... # Plugin components
marketplace.json Schema (Minimal Registry)
The marketplace configuration acts as a lightweight registry pointing to plugins. Each plugin entry only needs name and source.
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 · 277 lines · 2,669 tokens per session scan A 41c22dca3b0a
ai-coding-tools AGENTS.md is an instructions file published in the GitHub repository shopwareLabs/ai-coding-tools (42 stars, last pushed yesterday), licensed MIT. It adds 2,669 tokens to every session, about $0.0133 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
claude-code-marketplace CLAUDE.md
Claude Code instructions for NikiforovAll/claude-code-marketplace, covering project, commands, architecture, key concepts and linting.
awesome-claude-plugins CLAUDE.md
Claude Code instructions for Chat2AnyLLM/awesome-claude-plugins, covering awesome-claude-plugins development guidelines, active technologies, project structure, commands and code style.
claude-plugins CLAUDE.md
Instructions for tomoking2004/claude-plugins: Claude Code プラグインのマーケットプレイス．構成・導入・開発規約は README.md，美の基準は plugins/refine/BEAUTY.md を参照し，全ての成果物に適用する．.
claude-code-plugins AGENTS.md
AGENTS.md instructions for melodic-software/claude-code-plugins, covering claude-code-plugins, validate a change and conventions that load on demand.
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.