What is lead-dev-os CLAUDE.md?

Repository instructions for lead-dev-os, a Claude Code plugin that organizes product planning, specifications, and implementation tasks. A plugin is an add-on that extends an agent's behavior.

Working on the plugin structure, its skills, marketplace installation, target projects, specifications, and scoped development tasks.

They clarify the project's terminology, which files belong to the distributed plugin, and how its skills and specifications should be organized.

How CaptainMe-AI/lead-dev-os configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CaptainMe-AI/lead-dev-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CaptainMe-AI/lead-dev-os/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/CaptainMe-AI/lead-dev-os

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/captainme-ai/lead-dev-os/claude-md/github.svg)](https://agentmods.dev/instructions/captainme-ai/lead-dev-os/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/captainme-ai/lead-dev-os/claude-md"><img src="https://agentmods.dev/badge/instructions/captainme-ai/lead-dev-os/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/captainme-ai/lead-dev-os/claude-md"><img src="https://agentmods.dev/badge/instructions/captainme-ai/lead-dev-os/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,706 This file is loaded in full into every session.

When invoked 1,706 The same file — it is already loaded in full.

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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01706	$0.01706
Opus 5.5	$0.00682	$0.00682
Sonnet 5.5	$0.00341	$0.00341
Haiku 4.5	$0.00171	$0.00171

Measured 2mo ago against content hash 05d5cd8fb11c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lead-dev-os 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 2mo 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.

CLAUDE.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Dev instructions for the lead-dev-os repository itself.

Project

lead-dev-os is a Claude Code plugin — a spec & context-driven framework for Claude Code development on large projects. It provides structured skills for product planning, spec writing, task scoping, and context-aware implementation.

The plugin lives in the lead-dev-os/ subdirectory. Everything outside that directory is repository-level supporting infrastructure (tests, docs, legacy code) and is not part of the distributed plugin.

License

MIT License

Terminology

plugin — the lead-dev-os/ directory; this is what users point --plugin-dir at or install via a marketplace
target project — the project where the lead-dev-os plugin is installed/enabled
spec — a feature specification (created in the target project)
task — a scoped unit of work to be executed by the AI agent
skill — a directory under lead-dev-os/skills/ containing a SKILL.md file; invoked as /lead-dev-os:<skill-name>

Plugin Architecture

This project follows the Claude Code plugin structure:

Manifest: lead-dev-os/.claude-plugin/plugin.json — defines plugin metadata (name, version, description, author, etc.). The name field (lead-dev-os) is the namespace prefix for all skills.
Skills: lead-dev-os/skills/ — flat directory of skill folders, each containing a SKILL.md entrypoint. Skills may include supporting files (templates, examples, scripts) alongside SKILL.md. Claude Code auto-discovers skills from this directory.
Marketplace: .claude-plugin/marketplace.json at the repository root — the captainme-ai marketplace catalog listing the plugin with a relative-path source ("./lead-dev-os"). This must live at the repo root (not inside the plugin) so /plugin marketplace add CaptainMe-AI/lead-dev-os finds it. See Plugin marketplaces.
Inside the plugin, only plugin.json goes in lead-dev-os/.claude-plugin/. All other directories (skills/, etc.) are at the plugin root level. Never put marketplace.json there — it would make Claude Code treat the plugin directory as a marketplace.

Read the full file on GitHub · 122 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.

2mo ago First seen · 122 lines · 1,706 tokens per session scan A 05d5cd8fb11c

Subscribe to this mod's changes

lead-dev-os CLAUDE.md is an instructions file published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,706 tokens to every session, about $0.0068 per session on Opus 5.5. 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.

agentic-development agentic-workflow claude claude-code-plugin lead-dev-os lead-developer

lead-dev-os CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lead-dev-os CLAUDE.mdCaptainMe-AI/lead-dev-os	Instructions file	2	2mo ago	MIT	A	1,706	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

lead-dev-os: Instructions file for Claude Code