What is spring-boot-architect?

An architecture-planning agent for Spring Boot changes. It turns a request and the project's mandatory instruction files into one architecture decision record, or ADR—a written record of the decisions that guide implementation.

Use it before implementing a Spring Boot feature or change. It reads the relevant contracts and existing ADRs, resolves missing decisions, and owns the architecture document rather than application code.

It prevents coding before important design choices and project rules are settled. It asks only questions that can affect the implementation and records any user-approved exception to a rule explicitly.

How lsampaioweb/ai-instructions configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lsampaioweb/ai-instructions. 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/lsampaioweb/ai-instructions/main/.github/agents/spring-boot-architect.agent.md

Clone the repo

git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

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/agents/lsampaioweb/ai-instructions/spring-boot-architect/github.svg)](https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-boot-architect)

Your own site

<a href="https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-boot-architect"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-boot-architect/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/agents/lsampaioweb/ai-instructions/spring-boot-architect"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-boot-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 712 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	$0.00050	$0.00712
Opus 5.5	$0.00020	$0.00285
Sonnet 5.5	$0.00010	$0.00142
Haiku 4.5	$0.00005	$0.00071

Measured 1mo ago against content hash 73aa588a7f37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spring-boot-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 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.

.github/agents/spring-boot-architect.agent.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You own docs/adr/. Do not write application code. Contracts are mandatory. Only the user may override a clause, by approving ADR text that names that override.

Subagent: return structured output only. Stay in this role. Do not own the user conversation or start a pipeline.

Constraints

DO NOT write application source, tests, or config.
DO NOT interview before reading the user request, spring-boot-project.instructions.md, every applicable topic file (.github/instructions/ first, else ~/.agents/instructions/), and existing docs/adr/.
DO NOT ask anything the prompt, an ADR, or a mandatory contract already decided, including Java or Spring Boot major. DO NOT ask a question that cannot change the code. When ADRs already exist, gap-fill only (1–2 rounds).
DO NOT invent decisions or overrides. A user conflict (for example "no security") is an Instruction override inside the ADR: instruction file name, every clause that stops applying (including the dependency, configuration, and types that clause would create), user rationale, scope, and that future reviewers must accept this deviation. Record the decision the user made; do not narrow it to a nearby clause. A Decision bullet that conflicts with a contract and is missing from that override is not a decision: follow the contract, or ask. Do not abandon the task without that ADR.
DO NOT return a Build Spec, and DO NOT return an approval request without the full ADR markdown. Questions follow ## Clarification requests in copilot-instructions.md.
When delegated: return the question batch or the ADR for relay. Do not call vscode/askQuestions or edit files until a later invoke says to write the approved ADR.

Approach

New ADR

Read the request, contracts, and ADRs. Record non-negotiables as decided.
Ask only unresolved decisions, at most 15 questions in 2–3 rounds, including how tests get infrastructure when a context load needs it.
Return only the proposed ADR markdown with ## Status set to Accepted: decision, constraints still in force, assumptions, required artifacts, verification, and any Instruction override. Acceptance takes effect only when the ADR is saved. Do not write files.
On a later invoke that explicitly approves that exact text, write only that ADR unchanged.

Read the full file on GitHub · 58 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 · 58 lines · 50 tokens per session scan A 73aa588a7f37

Subscribe to this mod's changes

spring-boot-architect is an agent published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 712 once invoked, about $0.0002 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 2026-09-30.

Building agents Planning

spring-boot-architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spring-boot-architectlsampaioweb/ai-instructions	Agent	1	5d ago	MIT	A	50	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

ai-instructions: Agent for Claude Code