What is skills CLAUDE.md?

Repository instructions for maintaining the vpaivag/skills Claude Code plugin marketplace and its skills bundle. They describe where skills, agents, manifests, and documentation belong.

Use them when changing skill folders, plugin metadata, agent files, the README, or the plugin version.

They reduce mistakes when adding, removing, renaming, or releasing skills and agents. They also clarify which files must stay in sync.

How vpaivag/skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vpaivag/skills. 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/vpaivag/skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vpaivag/skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vpaivag/skills/claude-md/github.svg)](https://agentmods.dev/instructions/vpaivag/skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vpaivag/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/vpaivag/skills/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vpaivag/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/vpaivag/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 851 This file is loaded in full into every session.

When invoked 851 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.

Model	Per session	Once invoked
Fable 5.1	$0.00851	$0.00851
Opus 5	$0.00426	$0.00426
Sonnet 5	$0.00170	$0.00170
Haiku 4.5	$0.00085	$0.00085

Measured 9d ago against content hash faab235e057a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skills 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 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.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skills

Claude Code plugin marketplace + skills bundle. Plugin name: skills. Marketplace name: vpaivag.

Each skill is a self-contained SKILL.md under skills/<name>/, loaded on demand by the harness when its trigger fires. The plugin also ships declared agents (agents/*.md, auto-discovered) and the static asset library for visual.html (assets/visual/).

Hard rules

SKILL.md frontmatter is load-bearing. Every skills/<name>/SKILL.md must start with YAML frontmatter containing name and description. The description is the trigger string the harness matches against user intent — edit it deliberately, not stylistically.
Adding/removing/renaming a skill touches three places. Keep them in sync:
1. skills/<name>/SKILL.md (the skill itself)
2. The skills array in .claude-plugin/plugin.json
3. The per-skill section + table of contents in README.md
Agents are the analogous rule with two places: agents/<name>.md (auto-discovered, no manifest entry) and the Agents table in README.md.
Version lives in plugin.json only. Bump version in .claude-plugin/plugin.json for each release. Do not add a version field to .claude-plugin/marketplace.json — omitting it lets every git commit count as a new version, which is what enables /plugin update to detect changes without a manual marketplace bump. (See https://code.claude.com/docs/en/plugin-marketplaces.)
Companion files live beside SKILL.md. Some skills reference siblings (e.g. skills/blueprint/CONTEXT-FORMAT.md, skills/blueprint/PLAN-FORMAT.md, skills/blueprint/QA-FORMAT.md). Don't move or rename them without updating the references inside SKILL.md and agents/*.md.
*-FORMAT.md files are contracts, enforced just-in-time. Skills and agents must instruct reading the format file immediately before writing its artifact ("now — not earlier, never from memory") and validating the written file against the format's Required list. Artifact formats use real YAML frontmatter and stable IDs (EB-n, AC-n, B-n) — never the retired > **Field:** blockquote style.
Preserve the user's voice in skill prose. Don't rewrite phrasing into a different style — the wording in each SKILL.md is intentional.
Static assets and vanilla client-side JS only. assets/visual/ may hold CSS, dependency-free browser JS, HTML templates, and the vendored mermaid.min.js (plugin-side only — never copied into suite dirs; opt-in per the rule in assets/visual/BLOCKS.md). No build step, no package managers, no runtime dependencies, no servers, no CI scaffolding.
Split context is the pipeline's design principle. qa-author sees only context.md; plan-critic sees one proposal; /qa never reads plan.md. Don't "improve" a skill or agent by giving a blind role more context — the blindness is the feature.

Read the full file on GitHub · 39 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.

9d ago First seen · 39 lines · 851 tokens per session scan A faab235e057a

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository vpaivag/skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 851 tokens to every session, about $0.0043 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.

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

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

skills: Instructions file for Claude Code