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 skills add PIsberg/skill3 --skill vibetags-usagegit clone --depth 1 https://github.com/PIsberg/skill3Wrote 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/skills/pisberg/skill3/vibetags-usage)<a href="https://agentmods.dev/skills/pisberg/skill3/vibetags-usage"><img src="https://agentmods.dev/badge/skills/pisberg/skill3/vibetags-usage/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.
<a href="https://agentmods.dev/skills/pisberg/skill3/vibetags-usage"><img src="https://agentmods.dev/badge/skills/pisberg/skill3/vibetags-usage.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00262 | $0.11442 |
| Opus 5.5 | $0.00105 | $0.04577 |
| Sonnet 5.5 | $0.00052 | $0.02288 |
| Haiku 4.5 | $0.00026 | $0.01144 |
Grade A, and why
vibetags-usage 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.
This is a copy
95% identical to vibetags-usage — 1,255 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,039 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VibeTags Usage Guide
VibeTags is a compile-time Java annotation processor that generates AI platform-specific guardrail files from source annotations. Zero runtime overhead — all annotations have RetentionPolicy.SOURCE.
Quick Setup
1. Add the dependency
Maven (provided scope — compile-only):
<dependency>
<groupId>se.deversity.vibetags</groupId>
<artifactId>vibetags-processor</artifactId>
<version>1.0.0-RC1</version>
<scope>provided</scope>
</dependency>
Gradle:
compileOnly 'se.deversity.vibetags:vibetags-processor:1.0.0-RC1'
annotationProcessor 'se.deversity.vibetags:vibetags-processor:1.0.0-RC1'
2. Opt in to AI platforms (file-presence model)
VibeTags never creates files — it only updates files that already exist. Create empty placeholder files for each platform you want to support:
touch CLAUDE.md .claudeignore # Claude / Claude Code
touch .cursorrules .cursorignore # Cursor (traditional)
mkdir -p .cursor/rules # Cursor (granular per-class rules)
mkdir -p .trae/rules # Trae (granular per-class rules)
mkdir -p .roo/rules # Roo Code (per-class rules)
touch CONVENTIONS.md .aiderignore # Aider
touch QWEN.md .qwenignore # Qwen
touch .aiexclude gemini_instructions.md GEMINI.md # Gemini
touch AGENTS.md # Codex CLI
mkdir -p .github && touch .github/copilot-instructions.md .copilotignore # Copilot
touch llms.txt llms-full.txt # Windsurf Cascade / llms.txt standard
touch .windsurfrules # Windsurf IDE (traditional)
mkdir -p .windsurf/rules # Windsurf IDE (granular per-class rules)
touch .rules # Zed Editor
mkdir -p .cody && touch .cody/config.json .codyignore # Sourcegraph Cody
touch .supermavenignore # Supermaven
mkdir -p .continue/rules # Continue (granular per-class rules)
mkdir -p .tabnine/guidelines # Tabnine (granular per-class rules)
mkdir -p .amazonq/rules # Amazon Q (granular per-class rules)
mkdir -p .ai/rules # Universal AI standard (granular)
mkdir -p .pearai/rules # PearAI (granular per-class rules)
touch .mentatconfig.json # Mentat
touch sweep.yaml # Sweep (GitHub App)
touch .plandex.yaml # Plandex
touch .doubleignore # Double.bot
mkdir -p .interpreter/profiles && touch .interpreter/profiles/vibetags.yaml # Open Interpreter
touch .codeiumignore # Codeium
touch GEMINI.md # Gemini (official markdown)
touch .antigravityignore # Antigravity AI
touch .clinerules # Cline AI assistant
mkdir -p .junie && touch .junie/guidelines.md # JetBrains Junie
mkdir -p .kiro/steering # Amazon Kiro (granular per-class rules)
touch DESIGN.md # AI design agents (Cursor, Claude, Copilot, etc.)
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 · 1,039 lines · 262 tokens per session scan A bb61a7b68742
vibetags-usage is a skill published in the GitHub repository PIsberg/skill3 (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 262 tokens to every session and 11,442 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to vibetags-usage, differing in 1,255 lines, and is treated as a copy.
Other skills, from other repositories
spring-boot-engineer
Generates Spring Boot 3.x configurations, creates REST controllers, implements Spring Security 6 authentication flows, sets up Spring Data JPA repositories, and configures reactive WebFlux endpoints. Use when building Spring Boot 3.x applications, microservices, or reactive Java applications; invoke for Spring Data…
112-java-maven-plugins
Use when you need to add or configure Maven plugins in your pom.xml — including quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image build (Jib), build information tracking, and benchmarking (JMH) …
805-regulations-eu-cyber-resilience-act
Use when reviewing, designing, or modifying Java enterprise products, services, libraries, agents, plugins, connected components, or platform modules that may qualify as products with digital elements and need EU Cyber Resilience Act secure-by-design, vulnerability handling, security update, SBOM, product…
807-regulations-eu-digital-services-act
Use when reviewing, designing, or modifying Java enterprise systems that may support intermediary services, hosting services, online platforms, marketplaces, content moderation, recommender systems, advertising delivery, complaint workflows, transparency reporting, or systemic-risk evidence under the EU Digital…
808-regulations-eu-digital-markets-act
Use when reviewing, designing, or modifying Java enterprise systems that may support EU Digital Markets Act gatekeeper-platform concerns, core platform services, interoperability, business-user data access, consent-dependent data combination, ranking, self-preferencing, advertising transparency, or anti-circumvention…
810-regulations-eu-mifid-ii
Use when reviewing Java enterprise evidence for MiFID II investment services, investment activities, client classification, suitability, appropriateness, order-handling evidence, best-execution evidence, algorithmic-trading governance evidence, market-access governance evidence, transaction evidence, record keeping…