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.
npx agentmods add instructions/mehtrick/bjoern/agents-mdgit clone --depth 1 https://github.com/Mehtrick/bjoernWrote 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.
[](https://agentmods.dev/instructions/mehtrick/bjoern/agents-md)<a href="https://agentmods.dev/instructions/mehtrick/bjoern/agents-md"><img src="https://agentmods.dev/badge/instructions/mehtrick/bjoern/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00512 | $0.00512 |
| Opus 5 | $0.00256 | $0.00256 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
bjoern AGENTS.md 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 3d 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.
What it actually says
AGENTS.md
Build & Test
./gradlew build # compile + test (CI matrix: Java 8, 11, 17, 21)
./gradlew test # tests only (JUnit 5 platform)
./gradlew bjoerngen # generate abstract test classes from .zgr specs
./gradlew bjoerndoc # generate AsciiDoc documentation from .zgr specs
No separate lint or typecheck step — build covers compilation + tests.
Project Structure
Single-module Gradle plugin project (settings.gradle root = bjoern-gradle-plugin).
Source packages under src/main/java/de/mehtrick/bjoern/:
parser/— reads.zgr(YAML) spec files via Jacksongenerator/— produces Java test classes via JavaPoetdoc/— produces AsciiDoc via Freemarker templates (src/main/resources/*.ftlh)gradle/— plugin entry point (BjoernPlugin), tasks, extensionbase/— shared config model and custom exceptions
bjoern-sample/ is a standalone consumer project with its own Gradle wrapper.
Key Conventions
- Generated code is ephemeral. Files in
src/gen/are gitignored and regenerated on everybjoerngenrun. Never edit them. - Spec files use the
.zgrextension (YAML-based BDD: Feature/Background/Scenarios with Given/When/Then). - Use JavaPoet for Java code generation — never string concatenation.
- Use Freemarker (
.ftlh) for template-based doc generation. - Custom exceptions live in
base/:BjoernMissingPropertyException,BjoernGeneratorException,NotSupportedJunitVersionException. - Plugin version comes from
RELEASE_VERSIONenv var (set by CI on release tags); library version inversion.config. - Gradle wrapper is 8.4. README notes Gradle >7.6.2 required due to Jackson dependency bug.
Testing
- Tests use JUnit 5 (
useJUnitPlatform()) with AssertJ assertions. - Test specs (
.zgrfiles) live insrc/test/resources/. - Generated test output goes to
src/gen/(gitignored).
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.
- 3d ago First seen · 42 lines · 512 tokens per session scan A 9d096b87195d
bjoern AGENTS.md is an instructions file published in the GitHub repository Mehtrick/bjoern (4 stars, last pushed 12d ago), licensed MIT. It adds 512 tokens to every session, about $0.0026 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.
Other instructions, from other repositories
patchloom AGENTS.md
Instructions for patchloom/patchloom, covering agents.md, project overview, dev commands, git hygiene and release prs (release-please).
Perigon.CLI copilot-instructions.md
Instructions for AterDev/Perigon.CLI, covering github copilot instructions, general guidelines, 技术栈, 项目结构与分层 and 代码风格约定.
ducklab AGENTS.md
Instructions for jrullan/ducklab, covering working in this repository as an agent and path 1: conventional (edit the tree directly).
spine CLAUDE.md
Instructions for synaptixs/spine, covering spine — working on this repo, layout — where things live, invariants — break these and things get subtly wrong, gotchas that have bitten and before pushing.
harmont-cli CLAUDE.md
Instructions for harmont-dev/harmont-cli, covering testing, documentation, dsl and keep the sdk, hm init templates, and docs in sync.
HarnessSmith CLAUDE.md
Instructions for EpisodeYu/HarnessSmith, covering claude.md — harnesssmith 项目守则, 0. 协作模式与角色边界, 0.1 只能由人配置的环境(agent 不代劳), 1. think before coding and 2. thin first(薄优先 —— 本项目核心卖点,硬约束).