bleu

bleu is a plugin for Claude Code from Nirvaan05/Bleu-Plugin. Its manifest loads nothing; the 1 skill it bundles cost 194 tokens per session together, scanned A, original, MIT.

A Claude Code plugin that creates a detailed, file-based system plan from an idea before implementation. The plan uses Markdown and includes structured design information such as architecture decisions and action points.

In plain words
What is it for?
Use it for system design, architecture planning, specification-driven development, and maintaining a project knowledge base.
Why use it?
It keeps the reasoning behind a project in files instead of leaving it only in a chat. This gives coding work a clearer reference before code is written.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it for system design, architecture planning, specification-driven development, and maintaining a project knowledge base.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add Nirvaan05/Bleu-Plugin
/plugin install bleu
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.

Clone the repo
git clone --depth 1 https://github.com/Nirvaan05/Bleu-Plugin

Made for: Claude Code.

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 bleu

README.md
[![agentmods](https://agentmods.dev/badge/plugins/nirvaan05/bleu-plugin/bleu/github.svg)](https://agentmods.dev/plugins/nirvaan05/bleu-plugin/bleu)
Your own site
<a href="https://agentmods.dev/plugins/nirvaan05/bleu-plugin/bleu"><img src="https://agentmods.dev/badge/plugins/nirvaan05/bleu-plugin/bleu/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for bleu

Your own site · 80×15
<a href="https://agentmods.dev/plugins/nirvaan05/bleu-plugin/bleu"><img src="https://agentmods.dev/badge/plugins/nirvaan05/bleu-plugin/bleu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 194 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

bleu 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 1mo 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.

plugins/bleu/.claude-plugin/plugin.json · 30 lines

What it actually says

{
  "name": "bleu",
  "description": "Claude Code plugin for living blueprints. Turn an idea into a deeply structured, lint-passing, file-backed system plan before writing any code.",
  "version": "1.0.0",
  "license": "MIT",
  "author": {
    "name": "Nirvaan Lagishetty"
  },
  "homepage": "https://github.com/Nirvaan05/Bleu-plugin",
  "repository": "https://github.com/Nirvaan05/Bleu-plugin",
  "keywords": [
    "claude-code",
    "claude-code-plugin",
    "claude-code-skill",
    "claude-skills",
    "anthropic",
    "agent-skills",
    "subagents",
    "spec-driven",
    "spec-driven-development",
    "planning",
    "blueprint",
    "architecture",
    "knowledge-base",
    "wiki",
    "adr",
    "system-design"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 194 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 1mo ago First seen · 30 lines scan A 9e8c29c0e89f

Subscribe to this mod's changes

bleu is a plugin published in the GitHub repository Nirvaan05/Bleu-Plugin (4 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Related

Other plugins, from other repositories

team-kit

A team's shared Claude Code setup: an onboarding skill and a read-only reviewer for the shared configuration.

wesammustafa/Claude-Code-Everything-You-Need-to-Know · not measured

vibeframe

A control plane for agentic coding: a living, in-repo model of intent, architecture, and code — deterministically indexed, bidirectionally linked, continuously drift-checked. Bundles the VibeFrame MCP server, deterministic hooks, and workflow commands.

jubayertalha/vibeframe · not measured

agent-flow

A side pane that draws the session's agent flow live: the main loop's context window, every subagent it spawns as a tree, and for each one the context handed down (its prompt, or the whole parent context for a fork), what it did with it (steps, tools, context size) and the answer it handed back up. Docked beside the…

davila7/claude-code-templates · not measured

git-sidebar

A lazygit-style side pane: every worktree of the repository and its local branches as rows you click. A worktree row moves the session there with /cd; a branch row shows its last commits and offers switch (clean tree only) or open worktree. Docked floor to ceiling beside the transcript in the fullscreen layout, above…

davila7/claude-code-templates · not measured

tool-timing-badge

Times every tool call and wraps the engine's ToolUse rendering with a colored duration badge from the surface's own element table, on the terminal, Desktop and mobile. Hooks tool.call and ui.render using JSX.

davila7/claude-code-templates · not measured

pong

Pong above the Claude Code prompt: first to 5 against the computer. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs an interactive terminal with a mouse.

davila7/claude-code-templates · not measured