brownfield-onboarding

brownfield-onboarding is a skill for Claude Code from loiane/specs-driven-development-spring-angular. It costs 47 tokens per session (973 once invoked), scanned A, original, MIT.

A guide for bringing an existing Java Spring application into a workflow where features are described before they are built. It records the current codebase and its existing quality problems as a starting point.

In plain words
What is it for?
It helps inspect the Java and Spring setup, record build and test details, run the project's checks, document existing failures, and create a first design document that matches the code.
Why use it?
Older projects often have accumulated lint, test, coverage, and security issues that should not prevent new work. This gives the team a measured baseline and improves standards gradually.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./.githu.github/scripts/harness.sh --baseline > .specs/_baseline.json.

Good fit It helps inspect the Java and Spring setup, record build and test details, run the project's checks, document existing failures, and create a first design document that matches the code.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angular
agentmods
npx agentmods add skills/loiane/specs-driven-development-spring-angular/brownfield-onboarding

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.

agentmods badge for brownfield-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/loiane/specs-driven-development-spring-angular/brownfield-onboarding/github.svg)](https://agentmods.dev/skills/loiane/specs-driven-development-spring-angular/brownfield-onboarding)
Your own site
<a href="https://agentmods.dev/skills/loiane/specs-driven-development-spring-angular/brownfield-onboarding"><img src="https://agentmods.dev/badge/skills/loiane/specs-driven-development-spring-angular/brownfield-onboarding/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.

agentmods 80×15 button for brownfield-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/loiane/specs-driven-development-spring-angular/brownfield-onboarding"><img src="https://agentmods.dev/badge/skills/loiane/specs-driven-development-spring-angular/brownfield-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 973 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00973
Opus 5.5 $0.00019 $0.00389
Sonnet 5.5 $0.00009 $0.00195
Haiku 4.5 $0.00005 $0.00097

Measured 1mo ago against content hash 2619bff58f41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brownfield-onboarding 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/skills/brownfield-onboarding/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brownfield onboarding

Goal

Reach a state where /spec works on the next feature, the harness runs green (or with documented baseline drift), and the team is not blocked by years of accumulated lint/coverage debt.

Steps

  1. Detect the stack. Run .github/scripts/detect-stack.sh > .specs/_stack.json. Record:

    • Java version, Spring Boot version
    • DB engine (Postgres/MySQL/H2/…)
    • Migration tool (Flyway/Liquibase/none/both)
    • Test stack (JUnit 4 vs 5, Testcontainers presence)
    • Build tool (Maven only for now)
    • OpenAPI spec presence
  2. Run the harness once, capture baselines.

    ./.githu.github/scripts/harness.sh --baseline > .specs/_baseline.json
    

    Result is committed:

    {
      "captured_at": "2026-04-18T10:00:00Z",
      "git_sha": "abc1234",
      "checkstyle": { "violations": 412 },
      "spotbugs": { "high": 3, "medium": 27, "low": 88 },
      "jacoco": { "overall_line": 0.71, "overall_branch": 0.58 },
      "pit": { "kill_rate": 0.46, "scope": "incremental" },
      "archunit": { "violations": 18 },
      "openapi": { "present": false },
      "dependency_check": { "high": 1, "critical": 0 }
    }
    
  3. Add missing harness layers to the POM. Use maven-harness-pom skill. Pin to current values, not the targets:

    • JaCoCo <minimum> set to current minus 1% (ratchet).
    • PIT enabled in a profile (-Ppit), incremental scope only.
    • ArchUnit rules added with FreezingArchRule.freeze(...).
    • Spotless added in check mode for new code only initially (use <ratchetFrom>origin/main</ratchetFrom>).
  4. Generate a starter design. spring-architect reads the codebase and writes .specs/_starter-design.md describing modules-as-they-are, the dominant patterns, and notable deviations. This is the reference for future feature designs ("we already do X, so a new feature should follow X unless an ADR says otherwise").

  5. Document the gaps. Write .specs/_known-debt.md listing the things that fail or barely pass:

Read the full file on GitHub · 84 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. 1mo ago First seen · 84 lines · 47 tokens per session scan A 2619bff58f41

Subscribe to this mod's changes

brownfield-onboarding is a skill published in the GitHub repository loiane/specs-driven-development-spring-angular (62 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 973 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 2026-08-30.

Related

Other skills, from other repositories

spec-kitty-orchestrator-api-operator

Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows from outside the host CLI. Triggers: "use orchestrator-api", "build a custom orchestrator", "automate externally", "integrate CI with spec-kitty", "call spec-kitty from another tool", "orchestrator contract", "external…

Priivacy-ai/spec-kitty · 125 tokens

spk-integrate-orchestrator-api

Use Spec Kitty orchestrator-api from external systems, respecting host boundaries, state contracts, and workflow commands.

Priivacy-ai/spec-kitty · 30 tokens

806-regulations-eu-data-act

Use when reviewing, designing, or modifying Java enterprise systems that expose, exchange, store, process, export, or port data across users, businesses, connected products, cloud providers, APIs, event streams, AI data pipelines, data spaces, or SaaS platforms and need EU Data Act engineering controls. This should…

jabrena/plinth · 139 tokens

123-java-design-patterns

Use when you need to select, review, or implement Java design and integration patterns — including classic Java design patterns, REST API patterns, Kafka and event-driven patterns, database and persistence patterns, and cross-cutting integration patterns. This should trigger for requests such as Apply Java design…

jabrena/plinth · 89 tokens

125-java-concurrency

Use when you need to apply Java concurrency best practices — including thread safety fundamentals, ExecutorService thread pool management, concurrent design patterns like Producer-Consumer, asynchronous programming with CompletableFuture, immutability and safe publication, deadlock avoidance, virtual threads…

jabrena/plinth · 133 tokens

301-frameworks-spring-boot-core

Use when you need to review, improve, or build Spring Boot 4.0.x applications — including proper usage of @SpringBootApplication, component annotations (@Controller, @Service, @Repository), bean definition and scoping, configuration classes and @ConfigurationProperties (with @Validated), component scanning…

jabrena/plinth · 165 tokens