blueprint

blueprint is a command for coding agents from eddiebelaval/squire. It costs 0 tokens per session (5,776 once invoked), scanned A, original, MIT.

A command that creates an interactive HTML plan for building a project or feature. The plan stays on disk, tracks completed work with checkboxes, groups parallel tasks, and includes prompts for each phase.

In plain words
What is it for?
Use it to interview through project requirements, inspect the codebase, create a full build plan, or update an existing plan from a file.
Why use it?
It keeps the project plan available across sessions instead of losing it when a conversation ends or runs out of context.

Command

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 commands/eddiebelaval/squire/blueprint
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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 blueprint

README.md
[![agentmods](https://agentmods.dev/badge/commands/eddiebelaval/squire/blueprint.svg)](https://agentmods.dev/commands/eddiebelaval/squire/blueprint)
Your own site
<a href="https://agentmods.dev/commands/eddiebelaval/squire/blueprint"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/blueprint.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,776 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.05776
Opus 5 $0.00000 $0.02888
Sonnet 5 $0.00000 $0.01155
Haiku 4.5 $0.00000 $0.00578

Measured 5d ago against content hash a4d82597f497, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blueprint 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 5d 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.

commands/blueprint.md · 639 lines

How it starts

The opening of the file, as written. The whole thing — 639 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/blueprint - Interactive Build Plan Generator

Generate a persistent, interactive HTML build plan that serves as the master blueprint for an entire project or feature. Unlike session plans that die when context fills up, blueprints are HTML artifacts that live on disk, track progress with checkboxes, batch parallel work, and include copy-paste prompts for every phase.

This is the GPS, not the rearview mirror. /visualize explains what exists. /blueprint plans what to build.

Arguments

  • [project-or-feature]: What to blueprint (can be rough — you'll interview for details)
  • Flags: --update (update existing blueprint instead of creating new), --from-plan <file> (seed from an existing plan file)

Instructions

Phase 1: Conversational Intake (Structured Interview)

This is a multi-round structured interview. Use AskUserQuestion aggressively to nail down specifics. Eddie often speaks by voice — capture the essence, then confirm with structured questions. Do NOT skip to HTML generation until every round is complete.

IMPORTANT: Actually explore the codebase between questions. Read files, check the database schema, look at existing patterns. The blueprint should be grounded in reality, not assumptions. Use what you find to inform better questions.

Round 1: Scope & Vision

Use AskUserQuestion to establish:

  • What are we building? (options: New project from scratch / New feature in existing project / Rebuild or major refactor / Multi-project integration)
  • What's the scale? (options: Single feature (1-2 days) / Feature set (3-5 days) / Full product build (1-2 weeks) / Major platform (2+ weeks))
  • Who's the audience? Free-form conversation about users, clients, stakeholders.

Then explore the codebase — read existing files, understand what's already there.

Round 2: Architecture Decisions

Use AskUserQuestion for every significant technical choice:

  • Tech stack decisions — Framework, database, hosting, APIs (present 2-4 options with trade-offs)
  • Data model — What entities exist? What's the schema? (present options if multiple valid approaches)
  • Integration points — What external services, APIs, or systems does this touch?
  • Auth/security model — How is access controlled?

Read the full file on GitHub · 639 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. 5d ago First seen · 639 lines · 0 tokens per session scan A a4d82597f497

Subscribe to this mod's changes

blueprint is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,776 tokens. 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.