vibetags: Skill for Claude Code

.claude/skills/add-annotation/SKILL.md

add-annotation is a skill for Claude Code from PIsberg/vibetags. It costs 90 tokens per session (3,038 once invoked), scanned A, original, MIT.

A development guide for adding a new @AI... guardrail annotation to the VibeTags Java library. An annotation is a label placed on code that tools can read to apply a rule or record information.

In plain words
What is it for?
Use it when designing a new annotation, connecting it to platform output and validation, updating build fingerprints, and revising the related documentation.
Why use it?
It identifies all the library locations that must be updated so the new annotation is recognized consistently and keeps the annotation source-only, with no runtime cost.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Codex.

This is PIsberg/vibetags's own configuration. It tells Claude Code how to work on vibetags itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibetags configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd examples/basic && mvn clean compile && cd ../...

Reuse

Borrowing it

Nothing to install: this file belongs to PIsberg/vibetags. 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/PIsberg/vibetags/main/.claude/skills/add-annotation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PIsberg/vibetags

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 add-annotation

README.md
[![agentmods](https://agentmods.dev/badge/skills/pisberg/vibetags/add-annotation/github.svg)](https://agentmods.dev/skills/pisberg/vibetags/add-annotation)
Your own site
<a href="https://agentmods.dev/skills/pisberg/vibetags/add-annotation"><img src="https://agentmods.dev/badge/skills/pisberg/vibetags/add-annotation/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 add-annotation

Your own site · 80×15
<a href="https://agentmods.dev/skills/pisberg/vibetags/add-annotation"><img src="https://agentmods.dev/badge/skills/pisberg/vibetags/add-annotation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,038 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 166
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 172
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00090 $0.03038
Opus 5 $0.00045 $0.01519
Sonnet 5 $0.00018 $0.00608
Haiku 4.5 $0.00009 $0.00304

Measured 9d ago against content hash 45d4d3f26e2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

add-annotation 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 9d 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/add-annotation/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add an Annotation to VibeTags

Paths and class names below were derived from the codebase at v1.0.0-RC3 (the NewAnnotationsV5 wave — @AIIdempotent, @AIFeatureFlag, @AISecure — plus commit df01cb8, which fixed BuildFingerprint silently ignoring 12 annotation buckets and is why Step 5 below is not optional). If a path 404s, grep -rln "AISecure" vibetags/src/main/java from the repo root will re-locate every dispatch point this skill lists — @AISecure is the newest full annotation and touches every one of them.

Step 1 — Design the annotation

New file: vibetags-annotations/src/main/java/se/deversity/vibetags/annotations/AIYourName.java.

  • @Retention(RetentionPolicy.SOURCE) always — zero runtime cost is a hard invariant of this library; nothing about the annotation may require CLASS or RUNTIME retention.
  • @Target({...}) — pick from TYPE, METHOD, FIELD, PARAMETER to match the semantic (e.g. @AIInputSanitized/@AISecureLogging target PARAMETER, FIELD, not TYPE).
  • String attributes default to "", never null — every consumption site checks .isBlank()/.isEmpty(), never a null-check.
  • Enum-valued attributes get a nested enum inside the @interface with a sensible default constant (see AIThreadSafe.Strategy, AIExtensible.Strategy, AISecureLogging.MaskingPolicy).
  • Class-valued attributes (AISunset.replacement) cannot be read below the model seam at all: calling them during annotation processing throws MirroredTypeException. Resolve the value once, in AnnotationCollector.record(...) — the only place the compiler is still in scope — and store it with builder.typeMember("AIYourName.attr", …). Consumption sites then read element.typeMember("AIYourName.attr", "<fallback>"). Copy the AISunset pattern; do not reintroduce a try/catch in a formatter or renderer, since ArchitectureRulesTest forbids javax.lang.model there and the catch would never fire anyway.
  • Full Javadoc on the @interface and every attribute — docs/ANNOTATIONS.md's semantics bullet and the vibetags-usage skill's per-annotation section are meant to summarize it, not invent it.

Read the full file on GitHub · 192 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. 9d ago First seen · 192 lines · 90 tokens per session scan A 45d4d3f26e2b

Subscribe to this mod's changes

add-annotation is a skill published in the GitHub repository PIsberg/vibetags (15 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 3,038 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

spring-boot-development

Comprehensive Spring Boot development skill covering auto-configuration, dependency injection, REST APIs, Spring Data, security, and enterprise Java applications.

manutej/luxor-claude-marketplace · 31 tokens

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…

eric861129/SKILLS_All-in-one · 91 tokens

java-architect

Use when building, configuring, or debugging enterprise Java applications with Spring Boot 3.x, microservices, or reactive programming. Invoke to implement WebFlux endpoints, optimize JPA queries and database performance, configure Spring Security with OAuth2/JWT, or resolve authentication issues and async processing…

eric861129/SKILLS_All-in-one · 67 tokens

java-boilerplate

Gera automaticamente getters, setters, construtores, toString, equals e hashCode para classes Java. Triggers on: /java-boilerplate, 'gerar métodos java', 'criar getters setters'.

chidekina/aria-superpowers · 48 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens