agentmods.dev

vibetags: Instructions file for Claude Code

CLAUDE.md

vibetags CLAUDE.md is an instructions file for Claude Code from PIsberg/vibetags. It costs 3,084 tokens per session, scanned A, original, MIT.

Project instructions for VibeTags, a Java annotation processor that creates AI-platform guardrail files from source-code annotations. They define build checks, file-writing rules, tests, and project boundaries.

In plain words
What is it for?
Use them when changing VibeTags to understand its modules, run the required tests, follow annotation and file-generation rules, and keep documentation and code boundaries intact.
Why use it?
They protect important project guarantees, such as preserving hand-written content and writing configuration files only in allowed cases.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; 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 ../vibetags && mvn clean install.

not rated 15repo +1 changed 3d ago A scan 3,084 tokens original MIT
View source ↗ PIsberg/vibetags
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.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 vibetags CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pisberg/vibetags/claude-md.svg)](https://agentmods.dev/instructions/pisberg/vibetags/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pisberg/vibetags/claude-md"><img src="https://agentmods.dev/badge/instructions/pisberg/vibetags/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,084 This file is loaded in full into every session.
When invoked 3,084 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03084 $0.03084
Opus 5 $0.01542 $0.01542
Sonnet 5 $0.00617 $0.00617
Haiku 4.5 $0.00308 $0.00308

Measured 3d ago against content hash 96abce624cc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vibetags CLAUDE.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.

CLAUDE.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

VibeTags is a compile-time Java annotation processor (AIGuardrailProcessor) that generates AI platform guardrail files from @AI* annotations. Module map and per-subproject notes: docs/ARCHITECTURE.md. The reasoning behind every invariant below: docs/LOAD-BEARING.md.

Tier-1 invariants

Each line names its enforcing check; run it, do not just read this list.

  1. File presence is the only platform opt-in; never create an output file (sole exception: the codex sidecar). GuardrailLifecycleEndToEndTest
  2. Hand-authored content outside VIBETAGS-START/END markers must never be lost. GuardrailFileRecoveryEndToEndTest, MarkerInjectionTest
  3. process() returns false; all writing happens on processingOver(). AIGuardrailProcessorProcessTest
  4. AGENTS.md is written only as the sole AI config file, or with an existing marker pair. AgentsMdSoleFallbackTest
  5. All 44 annotations stay RetentionPolicy.SOURCE. AnnotationDefinitionsTest
  6. An aggregate collapses to a scoped-rules index when its granular directory is opted in; the safety buckets stay inline. GranularRulesEndToEndTest
  7. The rendering layer (internal/content/) never imports compiler APIs. ArchitectureRulesTest
  8. A new validation check is a rule entry under internal/validation/, never a loop in AnnotationValidator. ValidationRuleUnitTest
  9. Adding a platform or annotation follows the add-platform / add-annotation skill, never improvisation.
  10. A YAML renderer declares mergeShape(); a marker-free renderer whose file varies declares wholeFileMerge(). YamlMergeShapeContractTest, MultiModuleWholeFileMergeTest
  11. Dependency manifests live under a Java package path, never META-INF/. TransitiveGuardrailLifecycleE2ETest
  12. Anything that becomes generated content reaches BuildFingerprint. TransitiveFingerprintTest
  13. Granular rule files are written through ModuleSidecar.mergeGranular, never directly. MultiModuleGranularRoleMergeTest
  14. Version literals live in vibetags-parent/pom.xml and nowhere else; bump via tools/set-version.sh. BuildVersionParityTest
  15. Logging is law: domain.event key=value, reason= on every .skip, tested events are contracts. docs/LOGGING.md, GuardrailFileWriterLogContractTest
  16. Every module that compiles Java runs the same static-analysis stack, and each module keeps its own .mvn/jvm.config because Error Prone silently does not run without it. BuildToolchainParityTest

Read the full file on GitHub · 141 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. 3d ago Changed · +1 lines · +40 tokens per session 96abce624cc0
  2. 8d ago First seen · 140 lines · 3,044 tokens per session scan A 0c883c24f83b

Subscribe to this mod's changes

vibetags CLAUDE.md is an instructions file published in the GitHub repository PIsberg/vibetags (15 stars, last pushed today), licensed MIT. It adds 3,084 tokens to every session, about $0.0154 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.

JavaTestingWriting and docsaiai-toolsannotationannotationsclaude
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens