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/orin-dx/agent-plugins/claude-mdgit clone --depth 1 https://github.com/orin-dx/agent-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/orin-dx/agent-plugins/claude-md)<a href="https://agentmods.dev/instructions/orin-dx/agent-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/orin-dx/agent-plugins/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00581 | $0.00581 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
agent-plugins 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Guidelines (CLAUDE.md)
Quick reference guide for Claude Code CLI and Claude AI agents interacting with orin-dx/agent-plugins.
1. Quick Reference & Commands
- Install Plugin in Claude Code:
claude plugin add orin-dx/agent-plugins/ranger claude plugin add orin-dx/agent-plugins/mason - Install Plugin in AGY:
agy plugin add orin-dx/agent-plugins/ranger agy plugin add orin-dx/agent-plugins/mason - Local Manifest Validation:
jq . marketplace.json > /dev/null jq . plugins/*/plugin.json > /dev/null - Mermaid Diagram Validation (run after touching any mermaid-fenced block — a syntax error still reads as valid markdown, only an actual render catches it):
./scripts/check-mermaid.sh - Version Consistency (run after any version bump — checks
plugin.json, README, CHANGELOG, andmarketplace.jsonagree):./scripts/check-versions.sh - Skill Doc Accuracy (run after adding/removing/renaming a skill directory — checks every skill a README's table documents actually exists):
./scripts/check-skills-doc.sh - Reference File Size (run after editing any file in
shared/references/— a reference loaded via<load_first>is a fixed tax on every agent invocation that loads it, so it stays capped at 120 lines and split by concern):./scripts/check-reference-size.sh
2. Authoring Guidelines & Single Source of Truth
All authoring rules and principles are centralized in:
shared/constitution.md: EARS-format authoritative rules — the fence all plugin development must stay inside. Read this first.shared/agent-best-practices.md: Principles behind the constitution with examples — 5-part agent structure, EARS placement, cognitive modes, schema-driven handoffs, model/effort tiers.AGENTS.md: Repository standards, directory layout, and new-plugin checklist.
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.
- 3d ago First seen · 63 lines · 581 tokens per session scan A c6c0d13e5869
agent-plugins CLAUDE.md is an instructions file published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed today), licensed MIT. It adds 581 tokens to every session, about $0.0029 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
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
dxkit CLAUDE.md
Instructions for vyuh-labs/dxkit, covering claude.md — dxkit development rules, architecture rules, 1. tool invocation goes through the registry, 2. never duplicate tool invocation logic and 3. language facts come from detect.ts.
agent-skills AGENTS.md
AGENTS.md instructions for racastellanosm/agent-skills, covering agents.md, 1. vision & architectural invariants, 2. repository architecture & layout, 3. harness support & installation paths and 4. scripting & tooling guardrails.
devkit CLAUDE.md
Instructions for 5uck1ess/devkit, covering claude.md, layout, architectural invariants, conventions and fixing this file.
avvarre CLAUDE.md
Instructions for PralhadYadawad/avvarre, covering avvarre — claude code instructions, what is avvarre?, available slash commands, mcp tools and project memory (.avvarre/).
agentforge copilot-instructions.md
Instructions for mrzroot/agentforge, covering github copilot custom instructions, project: agentforge, coding guidelines, security & architecture and testing instructions.