agentmods.dev

Roadboard CLAUDE.md

Roadboard CLAUDE.md is an instructions file for coding agents from Maless88/Roadboard. It costs 7,828 tokens per session, scanned B, original, MIT.

Project instructions for Roadboard that define communication, coding, versioning, Git, and MCP operating rules. They require user-facing text in Italian while keeping source code in English.

In plain words
What is it for?
Working on Roadboard while following its code style, commit format, changelog process, temporary-file rules, and MCP onboarding procedures.
Why use it?
They give an AI assistant precise project conventions, reducing inconsistent formatting, language, version changes, and repository handling.

Instructions file

not rated 2 20d ago B scan 7,828 tokens original MIT
View the source file Maless88/Roadboard
Install

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.

agentmods
npx agentmods add instructions/maless88/roadboard/claude-md
Clone the repo
git clone --depth 1 https://github.com/Maless88/Roadboard

Wrote 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.

agentmods badge for Roadboard CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maless88/roadboard/claude-md.svg)](https://agentmods.dev/instructions/maless88/roadboard/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/maless88/roadboard/claude-md"><img src="https://agentmods.dev/badge/instructions/maless88/roadboard/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,828 This file is loaded in full into every session.
When invoked 7,828 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.07828 $0.07828
Opus 5 $0.03914 $0.03914
Sonnet 5 $0.01566 $0.01566
Haiku 4.5 $0.00783 $0.00783

Measured 4d ago against content hash d172a267761a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

Roadboard CLAUDE.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

# breaking every subsequent pnpm command for the normal user (fix: `sudo chown -R
CLAUDE.md · 579 lines

How it starts

The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

MASTER PROTOCOL

1. CODING RULES & COMMUNICATION

  • Language: All textual communication in Italian. All source code (variables, strings, docstrings) in English.
  • Verbosity: Minimal prose. No preambles, summaries, or unsolicited confirmations. Relevant output only. Code without explanations unless explicitly requested.
  • Airy Code Style:
    • EXACTLY 1 empty line before if, then, elif, else, try, except.
    • EXACTLY 2 empty lines before every class or def.
    • EXACTLY 1 empty line after a method docstring before the code.
  • Versioning: READ-ONLY. Never bump versions unless explicitly requested ("bump vX.Y.Z").
  • Hygiene: All temporary files/artifacts MUST stay in .agent/. Git-ignored and ephemeral.

2. PROJECT LIFECYCLE & GIT

  • Commits: Strictly follow Conventional Commits (type(scope): description). No versions in messages.
  • Changelog: When performing "BUMP vX.Y.Z", update both CHANGELOG.md and README.md following the Keep a Changelog standard.
    • Header: Use the format ## [X.Y.Z] - YYYY-MM-DD.
    • Structure: Categorize all changes under the following semantic subsections: ### Added, ### Changed, ### Deprecated, ### Fixed, ### Removed, or ### Security.
    • Style: Use plain indented bullet points for each change. Do not use bold text within the descriptions.
    • Sync: Ensure the version number and the latest "Added/Fixed" highlights are synchronized in the README.md.
  • Refactoring: Apply patches only. NO full refactoring without explicit consent.

3. MCP OPERATIONAL PROTOCOLS (AUTO-ONBOARDING)

  • Serena Module: If tools are available and you have NOT yet called initial_instructions() in this session, call it IMMEDIATELY — before any other response, even if the opening message seems generic.
  • RoadBoard 2.0 MCP: If tools are available and you have NOT yet called initial_instructions() in this session, call it IMMEDIATELY — before any other response, even if the opening message seems generic.
  • Context7 Module: You MUST use Context7 tools whenever the user asks a question about any programming language, framework, library, API, software tool, or technology stack.

Read the full file on GitHub · 579 lines

Changes

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.

  1. 4d ago First seen · 579 lines · 7,828 tokens per session scan B d172a267761a

Subscribe to this mod's changes

Roadboard CLAUDE.md is an instructions file published in the GitHub repository Maless88/Roadboard (2 stars, last pushed 20d ago), licensed MIT. It adds 7,828 tokens to every session, about $0.0391 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agent-toolsbullmqmcpmemgraphmodel-context-protocolmonorepo
Related

Other instructions, from other repositories

boardstate AGENTS.md

Instructions for 100yenadmin/boardstate, covering agents & boardstate, 1. give any ai the board (@boardstate/mcp), the tool catalog, conventions for board-building agents and 2. embed a chat agent in your host (@boardstate/agent).

100yenadmin/boardstate · 2,557 tokens

printyourduck-mcp AGENTS.md

AGENTS.md instructions for printyourduck/printyourduck-mcp, covering agent guide, product boundary, commands, repo ownership and release truth.

printyourduck/printyourduck-mcp · 522 tokens

mcpqueen AGENTS.md

AGENTS.md instructions for mcpqueen/mcpqueen, covering mcp queen repository instructions, product integrity, working tree, routine autonomous work and manual gates.

mcpqueen/mcpqueen · 744 tokens

mcp-hub CLAUDE.md

Claude Code instructions for ftaricano/mcp-hub, covering claude.md -- mcp-hub, o que e, stack & estrutura, como rodar / validar and setup.

ftaricano/mcp-hub · 895 tokens

mcp-hub AGENTS.md

AGENTS.md instructions for ftaricano/mcp-hub: As regras operacionais deste repo sao canonicas em CLAUDE.md (fonte unica para Claude/Codex/Hermes). Leia-o antes de tocar em codigo.

ftaricano/mcp-hub · 204 tokens

MCPs copilot-instructions.md

Copilot instructions for AceDataCloud/MCPs, covering copilot sync instructions for acedatacloud mcps, repository structure, source of truth, what to sync and rules.

AceDataCloud/MCPs · 287 tokens