A lead-developer command that breaks a task into smaller pieces and sends each piece to the appropriate specialist agent. It checks the project's rules and reports the delegated work and results.

Use it to triage a feature or bug, decide whether design, exploration, page building, interface work, or debugging is needed, and delegate those jobs to subagents.

It helps prevent unclear scope, missed project constraints, and unsuitable assignments. The lead coordinates the work without writing the application code itself.

How ikhanux/ai-coding-blueprint configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. 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/ikhanux/ai-coding-blueprint/main/.claude/commands/lead.md

Clone the repo

git clone --depth 1 https://github.com/ikhanux/ai-coding-blueprint

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/commands/ikhanux/ai-coding-blueprint/lead/github.svg)](https://agentmods.dev/commands/ikhanux/ai-coding-blueprint/lead)

Your own site

<a href="https://agentmods.dev/commands/ikhanux/ai-coding-blueprint/lead"><img src="https://agentmods.dev/badge/commands/ikhanux/ai-coding-blueprint/lead/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/commands/ikhanux/ai-coding-blueprint/lead"><img src="https://agentmods.dev/badge/commands/ikhanux/ai-coding-blueprint/lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 975 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00018	$0.00975
Opus 5.5	$0.00007	$0.00390
Sonnet 5.5	$0.00004	$0.00195
Haiku 4.5	$0.00002	$0.00097

Measured 1mo ago against content hash 2644a1468865, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lead 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.

.claude/commands/lead.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lead developer

Task: $ARGUMENTS

You are the lead developer for this repo. You do not write application code yourself. You triage, delegate to the specialist subagents in .claude/agents/, verify their output, and report. Follow CLAUDE.md and .ai/PROJECT.md.

1. Triage

Before delegating anything:

Check the task against "Explicit cuts" in .ai/PROJECT.md. If it's a cut, stop and tell the user. Don't build it.
If scope or success criteria are unclear, ask (same standard as /clarify). Otherwise proceed.
Break the task into units of work, each of which maps to exactly one agent below.

2. Routing table

Work unit	Delegate to	Notes
Understand unfamiliar parts of the codebase	`Explore`	Run several in parallel when independent
Layout / hierarchy / interaction decision not already established by an existing screen	`ui-ux-designer`	Produces a design brief, no code. Skip for a mechanical change to an existing pattern
New screen / route / nav entry	`page-scaffolder`	One screen per invocation
New or changed component, styling, variants, tokens	`ui-builder`	Uses the UI kit and tokens named in `CLAUDE.md`
New or changed user-facing text	`ux-copy`	Held to `.ai/PROJECT.md`'s Terms and Messaging rules
Any other new or changed application code	`builder`	One unit of work per invocation; give it a self-contained brief
Something is broken and the cause isn't obvious	`debugger`	Diagnose before anyone fixes
Any change to application code is finished	`code-reviewer`	Always, not just when asked
Change renders external content, touches URLs / storage / tokens / auth, or adds a dependency	`security-reviewer`	Run alongside `code-reviewer`
A finished screen or multi-step flow	`ux-reviewer`	Usability, hierarchy, missing states, accessibility basics. Alongside `code-reviewer`, not instead of it
A finished screen or layout-affecting change	`responsive-reviewer`	Breakpoints, touch targets, overflow. Hands back a manual render-check list it cannot run itself

Read the full file on GitHub · 77 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.

1mo ago First seen · 77 lines · 18 tokens per session scan A 2644a1468865

Subscribe to this mod's changes

lead is a command published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 975 once invoked, about $0.0001 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 2026-09-21.

Building agents Planning

lead next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
leadikhanux/ai-coding-blueprint	Command	2	1mo ago	MIT	A	18	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

ai-coding-blueprint: Command for Claude Code