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/myrialabs/clopen/claude-mdgit clone --depth 1 https://github.com/myrialabs/clopenWrote 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/myrialabs/clopen/claude-md)<a href="https://agentmods.dev/instructions/myrialabs/clopen/claude-md"><img src="https://agentmods.dev/badge/instructions/myrialabs/clopen/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 | $0.00772 | $0.00772 |
| Opus 5 | $0.00386 | $0.00386 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
clopen 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Guidelines
This document provides guidelines for Claude Code when working on the Clopen project.
WORK PROTOCOL
Before Coding
- Identify which stage is currently being worked on
- Understand the specific task that needs to be completed
- For PR-related tasks (e.g., "review PR #123", "check PR X"), read
MAINTAINERS.mdfirst to understand the PR workflow, review process, and maintainer conventions
During Coding
- Follow agreed-upon architecture and patterns
- Do not change technical decisions without discussion
- Ensure code matches the established folder structure
- Use chosen libraries and frameworks
- Do NOT run
bun run devorbun run buildcommands
After Coding
- Run
bun run checkandbun run lint; addbun run testwhen the change touches tested logic - Do not create any .md files unless explicitly instructed
- Hand back the three artifacts from CONTRIBUTING.md → Delivering a Change:
- Branch:
<type>/<description>— lowercase, kebab-case, concise - One commit:
<type>(<scope>): <subject>(imperative, lowercase, no period) plus a body — what broke, why it happened, what the change does about it, wrapped at 72 columns - PR description from the template, ready to paste — or a PR comment if the work extends an open PR
- Do NOT create the branch, commit, or PR automatically — draft all three for review
- Branch:
IMPORTANT RULES
- Be CONSISTENT with previously made decisions
- COMMUNICATE if existing plans need to be changed
- STOP after each stage for review
PROJECT-SPECIFIC GUIDELINES
Runtime & Package Manager
- Bun-only project — Node.js and Deno are NOT supported
- Always use
buncommands (never npm/pnpm/yarn) - Runtime checks exist in
bin/clopen.tsandbackend/index.ts
Architecture
- Backend: Bun + Elysia with WebSocket architecture
- Frontend: Svelte 5 with runes system ($state, $derived, $effect)
- Database: SQLite with migration system
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.
- 4d ago First seen · 98 lines · 772 tokens per session scan A 2824d9e10b1c
clopen CLAUDE.md is an instructions file published in the GitHub repository myrialabs/clopen (40 stars, last pushed yesterday), licensed MIT. It adds 772 tokens to every session, about $0.0039 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
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge testing.instructions.md
Testing rules for Plan Forge — vitest patterns, fake-timers vs tolerance, mocking conventions, and how to read test output without hallucinating failures. Auto-loads when editing test files.