A new project
A Spring Boot project from the Initializr, with a blueprint, executable boundaries and a green build. No business code. It carries its own .claude/.
An agent harness for Spring Boot on Claude Code.
guides · sensors · blueprints
32 skills·7 agentsin the harness, as of release v0.44.0 →It is not a coding assistant: it brings no model and no editor. It is not an agent framework: those build agents, this one constrains one. It is not a template: it generates through Spring Initializr at run time, and its job continues on every feature.
Nine blueprints in YAML, plus your own. One declaration feeds the model, the hook and the compiler.
Read more →One use case per run, designed layer by layer by an owner skill, approved by you, then frozen.
Read more →A forbidden import, a write outside a skill's territory, an edit to an approved spec, a force push: a hook refuses it. The model is not asked to remember.
Read more →A hook records each run: tokens per piece, the chain of skills, files touched, questions asked. It costs zero tokens, and /audit-usage aggregates the runs.
Read more →A generated project carries the whole harness and its own CI. /arch-adopt updates it later; below Spring Boot 4.0, /platform-upgrade gets it there first.
Read more →Every hook is one ArchHook.java, with no shell. CI injects each violation on Ubuntu, macOS and Windows and requires the block.
Read more →Teams adopt coding agents fast, each in its own way. Months later the same problems show up in every repository.
Each team writes its own prompts, skills and conventions. The company uses AI, but there is no one way to use it, and no way to compare results.
One harness exported into every project, from a blueprint in YAML.
A skill takes minutes to write. Keeping it scoped, named and current never ends, and a misspelled frontmatter field is ignored without a word.
A schema checked in CI; /arch-adopt updates without losing local edits.
Which agent may write which folder? Who approved the design? Without a rule in code, the agent decides, and the answer changes between runs.
Write territory per class, enforced by a hook. Deny by default.
Tokens go out per piece, per model, per run. Nobody can say which skill spent them, which files it touched, or what failed.
/audit-usage: tokens, model, files and failures per piece, at zero token cost.
The model reads a skill's description and decides whether it applies. Loaded in one run, skipped in the next, the same request yields different code.
Commands are typed, norms load by path, hooks run on every event.
The build is green and a domain class now imports a framework. It surfaces in code review weeks later, if at all.
forbidden_imports declared once, refused at write time.
Is enforcement active on this machine?
✅ operationalInitializr, blueprint, harness exported into the project.
20 minA short interview, one skill per layer, a frozen spec.
10 minA restricted executor in a clean session.
310 tests · 0 failTime, tokens and failures of every piece.
0 tokens to produceJDK 21+, git and curl. No Python, no Node, no shell scripts.
A Spring Boot project from the Initializr, with a blueprint, executable boundaries and a green build. No business code. It carries its own .claude/.
Installs the harness into a project born elsewhere, or updates one that is behind. It refuses a dirty worktree and stamps a hash for every file it writes.
Guide · /arch-adopt →/arch-adopt refuses that project. /platform-upgrade takes the build to the line the Initializr serves today:
test-diff tells what the upgrade broke from what was already brokenGENESIS.md @ f5eaf3b ↗build.yml @ a3cc28a ↗SonarQube Cloud @ 948c8dc ↗.arch-provenance.json @ a3cc28a ↗Nerviz does not draw these: GitHub and SonarQube Cloud render them on every visit.
$ git clone https://github.com/nerviz-ai/bank-app$ cd bank-app$ ./mvnw verify
JDK 21 and Docker. Without Docker, the integration tests are skipped. The latest main build printed:
[INFO] Tests run: 287, Failures: 0, Errors: 0, Skipped: 0[INFO] Tests run: 80, Failures: 0, Errors: 0, Skipped: 0[INFO] All coverage checks have been met.[INFO] BUILD SUCCESS
The whole story, use case by use case, on the Showcase →Everything it wrote is public →