Guidance for writing Bjoern specification files, which describe behaviour in YAML-like text for generating Java tests and documentation. Bjoern is a tool for turning these specifications into test code and AsciiDoc documents.

Use it when writing or reviewing .zgr files, describing acceptance tests and business rules, reusing statements, or generating Java test classes and documentation.

Specifications and generated files follow rules that are easy to break, and generated code should not be edited by hand. This guidance helps keep the specifications reusable and maintainable.

How Mehtrick/bjoern configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to Mehtrick/bjoern. 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/Mehtrick/bjoern/master/.agents/bjoern-zgr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Mehtrick/bjoern

Made for: Claude Code, Codex.

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/skills/mehtrick/bjoern/bjoern-zgr/github.svg)](https://agentmods.dev/skills/mehtrick/bjoern/bjoern-zgr)

Your own site

<a href="https://agentmods.dev/skills/mehtrick/bjoern/bjoern-zgr"><img src="https://agentmods.dev/badge/skills/mehtrick/bjoern/bjoern-zgr/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/skills/mehtrick/bjoern/bjoern-zgr"><img src="https://agentmods.dev/badge/skills/mehtrick/bjoern/bjoern-zgr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,664 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	$0.06664
Opus 5	$0.00025	$0.03332
Sonnet 5	$0.00010	$0.01333
Haiku 4.5	$0.00005	$0.00666

Measured 10d ago against content hash 4cd18ed22509, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bjoern-zgr 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 10d 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.

.agents/bjoern-zgr/SKILL.md · 948 lines

How it starts

The opening of the file, as written. The whole thing — 948 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Bjoern .zgr Files

How Bjoern Works

.zgr files (YAML-based BDD specs) are read by the parser
The generator creates abstract Java test classes + interfaces via JavaPoet
A Freemarker template produces AsciiDoc documentation
Gradle tasks: bjoerngen (code) and bjoerndoc (docs)

Generated code lives in src/gen/ and is regenerated on every run — never edit it.

When to Use Bjoern

Bjoern is ideal for acceptance-oriented tests where business logic is paramount and the specification serves as living documentation.

Test Type Suitability

Test Type	Suitability	Recommendation
Use Cases / User Journeys	★★★★★	Ideal - Primary use case
Acceptance Tests	★★★★★	Ideal - Stakeholders understand specs
Business Logic / Domain Rules	★★★★★	Ideal for complex domain rules
API Tests	★★★★☆	Very good with technical abstraction
Integration Tests	★★★★☆	Very good for multi-component workflows
UI Tests	★★★☆☆	Good with Page Object Pattern
Security Tests	★★★☆☆	Only for business security requirements
Unit Tests	★★☆☆☆	Only for complex business logic
Performance Tests	★☆☆☆☆	Not suitable

Use Cases (Primary Use Case)

Bjoern excels at testing use cases - complete user journeys that deliver business value.

What makes a good use case for Bjoern:

Has clear business value
Involves multiple steps/interactions
Has observable outcomes
Can be described in business language
Stakeholders care about the behavior

Example: E-Commerce Checkout Use Case

Feature: Customer checkout process

Scenario: Customer completes purchase with credit card
  Given:
    - Customer "alice" has items in cart
    - Cart total is "150" Euro
    - Customer has payment method "Credit Card"
  When:
    - Customer proceeds to checkout
    - Customer enters shipping address "Main St 123, Berlin"
    - Customer confirms payment with "Credit Card"
  Then:
    - Order is created with number "ORD-2024-001"
    - Payment of "150" Euro is processed
    - Confirmation email is sent to "[email protected]"
    - Cart is empty

Scenario: Checkout fails due to payment declined
  Given:
    - Customer "bob" has items in cart
    - Cart total is "200" Euro
    - Payment method "Credit Card" is declined
  When:
    - Customer proceeds to checkout
    - Customer confirms payment with "Credit Card"
  Then:
    - Order is not created
    - Error message is "Payment declined"
    - Cart still contains items
    - No email is sent

Read the full file on GitHub · 948 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.

10d ago First seen · 948 lines · 50 tokens per session scan A 4cd18ed22509

Subscribe to this mod's changes

bjoern-zgr is a skill published in the GitHub repository Mehtrick/bjoern (4 stars, last pushed 19d ago), licensed MIT. It adds 50 tokens to every session and 6,664 once invoked, about $0.0003 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.

Code Generation Testing Unit testing bdd-framework bdd-tests junit yaml

ordering-and-flakes

Control spec ordering and manage flaky specs — Serial, Ordered containers with BeforeAll/AfterAll/ContinueOnFailure, OncePerOrdered, SpecPriority, plus FlakeAttempts/--flake-attempts, MustPassRepeatedly, --repeat, and --until-it-fails. Use when specs must run in a fixed order, you need once-per-group setup, you're…

onsi/ginkgo · 111 tokens

parallelism

Run Ginkgo suites in parallel — ginkgo -p / --procs, the separate-process (not goroutine) model, SynchronizedBeforeSuite/SynchronizedAfterSuite vs BeforeSuite, GinkgoParallelProcess() for sharding ports/tmpdirs/databases, building a binary once via gexec, piping child-process output to GinkgoWriter, and what N…

onsi/ginkgo · 150 tokens

running

Run Ginkgo suites with the ginkgo CLI — run, -r, -p, --dry-run, watch, build (precompiled .test binaries), generate, outline, unfocus, labels, version; spec randomization (--randomize-all/--randomize-suites/--seed); running multiple suites (--keep-going/--skip-package/--compilers); previewing (--dry-run…

onsi/ginkgo · 142 tokens

tables-and-dynamic-specs

Parameterize and generate Ginkgo specs — DescribeTable/Entry table-driven specs, Entry descriptions (string, nil, closure, EntryDescription), PEntry/FEntry and per-Entry decorators, DescribeTableSubtree, generating specs in a construction-time loop, loading fixtures in TestXxx before RunSpecs, and shared-behavior…

onsi/ginkgo · 103 tokens

timeouts-and-async

Make Ginkgo specs interruptible and test asynchronous behavior — SpecContext/context.Context cancellable nodes, NodeTimeout/SpecTimeout/GracePeriod, the --timeout flag, Abort and SIGINT behavior, Gomega Eventually/Consistently (the func(g Gomega) form, .WithContext), and the defer GinkgoRecover() rule for goroutines.…

onsi/ginkgo · 106 tokens

writing-specs

Author good Ginkgo specs — container nodes (Describe/Context/When), subject nodes (It/Specify), setup/cleanup nodes (BeforeEach, JustBeforeEach, AfterEach, DeferCleanup, BeforeSuite/AfterSuite), the "declare in container, initialize in BeforeEach" rule, separating creation from configuration, reusable test helpers…

onsi/ginkgo · 120 tokens

bjoern: Skill for Claude Code