vibetags: Skill for Claude Code

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

add-platform is a skill for Claude Code from PIsberg/vibetags. It costs 107 tokens per session (2,890 once invoked), scanned A, original, MIT.

A development guide for adding a new output format or platform to VibeTags, the library that generates files for AI coding tools and related systems. It explains which registries, renderers, and writers need updating.

In plain words
What is it for?
Use it to support a new AI coding tool, IDE, pull-request reviewer, or context packer, including its generated file and any granular rules output.
Why use it?
It reduces the chance that a new generated file is wired into some parts of the library but missed in others.

Skill for Claude Code

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

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 →

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-platform/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-platform

README.md
[![agentmods](https://agentmods.dev/badge/skills/pisberg/vibetags/add-platform.svg)](https://agentmods.dev/skills/pisberg/vibetags/add-platform)
Your own site
<a href="https://agentmods.dev/skills/pisberg/vibetags/add-platform"><img src="https://agentmods.dev/badge/skills/pisberg/vibetags/add-platform.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,890 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: 1 finding, 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 144
    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 $0.00107 $0.02890
Opus 5 $0.00053 $0.01445
Sonnet 5 $0.00021 $0.00578
Haiku 4.5 $0.00011 $0.00289

Measured 8d ago against content hash 18df7afce1c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

add-platform 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 8d 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-platform/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add an AI Platform to VibeTags

Paths and class names below were derived from the codebase at v1.0.0-RC3 (commits 2bc839e Claude Code local/granular/Skill + Copilot granular, 9c61a83 AI PR-reviewers/context-packers/ Void/Roo, 406f353 Firebase AI — the smallest recent example). If a path below 404s, the architecture has drifted since — grep -rn "FIREBASE" vibetags/src/main/java from the repo root will re-locate every dispatch point this skill lists.

Step 0 — Decide the shape before touching code

  • New platform or new format of an existing one? Claude Code's local-override/granular/Skill additions were new formats of the already-listed "Claude" platform, so the README's **N AI platforms** count did not move. Only a genuinely new platform bumps that count.
  • Marker style is not your choiceGuardrailFileWriter.getMarkersFor(fileName) derives it from the extension: .md/.mdc/llms.txt/llms-full.txt → HTML comment markers; .json/ .toml → full overwrite, no markers; everything else → hash markers. Multi-module sidecar merge in generateFiles() is gated solely on "does this file get markers" — you do not write any sidecar-participation code either way.
  • Granular (one file per annotated class)? → goes through GranularRulesWriter, not a single-file PlatformRenderer.
  • Ignore-file family (a glob-pattern exclusion list driven only by @AIIgnore)? → reuse IgnoreFileRenderer, don't write a new renderer class.
  • Byte-identical output to an existing renderer? → delegate, don't reimplement (see FirebaseRenderer, which wraps a shared CursorRenderer instance).
  • Implicitly-activated sidecar of another service (codex_config/codex_rules under codex, qwen_settings/qwen_refactor under qwen, cody under cody)? → do not add its own key to ServiceRegistry.OPT_IN_KEYS; wire it into the special-case block at the bottom of GuardrailContentBuilder.build() instead.

Checklist (file by file)

Read the full file on GitHub · 159 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. 8d ago First seen · 159 lines · 107 tokens per session scan A 18df7afce1c3

Subscribe to this mod's changes

add-platform is a skill published in the GitHub repository PIsberg/vibetags (15 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 2,890 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.