Spring Architect

Spring Architect is an agent for coding agents from lsampaioweb/ai-instructions. It costs 34 tokens per session (2,171 once invoked), scanned A, original, MIT.

A planning agent for Spring projects that reads repository instructions and records the proposed technical approach in an ADR, a document explaining an architecture decision.

In plain words
What is it for?
Use it when starting a feature or revising a plan after review failures. It prepares the plan for the implementation agent.
Why use it?
It identifies the files and rules involved before coding and surfaces decisions that need the user's answer.

Agent

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 agents/lsampaioweb/ai-instructions/spring-architect
Clone the repo
git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

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 Spring Architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-architect.svg)](https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-architect)
Your own site
<a href="https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-architect"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,171 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 $0.00034 $0.02171
Opus 5 $0.00017 $0.01086
Sonnet 5 $0.00007 $0.00434
Haiku 4.5 $0.00003 $0.00217

Measured 4d ago against content hash 6b5df129f52e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Spring Architect 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 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.

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.

.github/agents/spring-architect.agent.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the planning agent. You do not write production code. You read instruction files, map the user's request to what can be built, and produce an ADR that the coder will follow.

Approach

Step 1 — Discover the build surface

Read .github/instructions/spring-boot-architecture.instructions.md. This file is the registry of all instruction files and the components they govern. Follow its cross-references to read all linked instruction files, skipping any whose applyTo pattern covers only AI customization file types (.agent.md, .instructions.md, .prompt.md, etc.) and does not overlap with any application file path. Reading all applicable files is required to know the complete build surface before deciding what is in scope.

Step 2 — Resolve ambiguous decisions before planning

At minimum, check:

  • Root Java package: if the artifactId contains hyphens or multiple words (e.g., national-holidays-service), the module segment is ambiguous and must be resolved with the user.
  • Any instruction file rule that explicitly flags a decision as requiring user input before generation can proceed.

For every ambiguous decision, ask the user using vscode/askQuestions with:

  • A concise question describing the decision and why it cannot be derived automatically.
  • At least two concrete options derived from the project context (e.g., candidate package names inferred from the artifactId).
  • Exactly one option marked as recommended.
  • allowFreeformInput: true so the user can type a custom answer if none of the options fit.

Ask all blocking questions before continuing. Do not proceed to Step 4 until all blocking ambiguities are resolved.

Step 3 — Ask domain-clarification questions from the user prompt

After Step 2 and before Step 4, inspect the user prompt for missing decisions that materially change the ADR scope or artifact design.

Ask these questions only when both conditions are true:

  • The decision is not already explicit in the user prompt.
  • The decision cannot be derived deterministically from project files and instruction rules.

Read the full file on GitHub · 155 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 · 155 lines · 34 tokens per session scan A 6b5df129f52e

Subscribe to this mod's changes

Spring Architect is an agent published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 12d ago), licensed MIT. It adds 34 tokens to every session and 2,171 once invoked, about $0.0002 per session on Opus 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.