What is bjorn-skills CLAUDE.md?

Instructions for maintaining bjorn-skills, a collection of reusable agent skill documents. The same skill folders can be used by several coding-agent tools and installed in multiple ways.

They guide contributors who add or edit skills, run the validation script, and check Claude Code marketplace and plugin manifests. A manifest is a file that describes a plugin or its contents.

They explain how the repository is structured and help keep skill files and plugin manifests consistent.

How Vingedal/bjorn-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Vingedal/bjorn-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/Vingedal/bjorn-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Vingedal/bjorn-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/vingedal/bjorn-skills/claude-md/github.svg)](https://agentmods.dev/instructions/vingedal/bjorn-skills/claude-md)

Your own site

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

Per session 1,099 This file is loaded in full into every session.

When invoked 1,099 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	$0.01099	$0.01099
Opus 5	$0.00549	$0.00549
Sonnet 5	$0.00220	$0.00220
Haiku 4.5	$0.00110	$0.00110

Measured 10d ago against content hash 32b4a48f36b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bjorn-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 10d 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 · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

bjorn-skills is a collection of cross-tool Agent Skills (the SKILL.md format). The same skills/<name>/ folder is consumed three ways from one source, with no conversion:

copied directly into any agent's skills directory (Codex CLI, Gemini CLI, Cursor, Copilot, or Claude Code manual),
installed via skills.sh (npx skills add Vingedal/bjorn-skills --skill <name>), and
installed as a standalone Claude Code plugin (<name>@bjorn-skills).

There is no application to build or run. The only executable code is the CI validator; everything else is skill content (Markdown) and plugin manifests (JSON). Work here means authoring/maintaining skill docs and keeping the manifests in sync.

Commands

# The repo's "test": validates every SKILL.md frontmatter + all JSON manifests. Runs in CI on push/PR.
python3 .github/scripts/validate_skills.py     # `python` also works on the Windows dev host

# Validate the Claude Code marketplace + plugin manifests (needs the claude CLI; not run in CI)
claude plugin validate .

There are no build/lint/unit-test steps — validate_skills.py is the only check.

Architecture: how one skill is wired in three places

A skill must stay consistent across three files:

skills/<name>/SKILL.md — the skill itself: YAML frontmatter (name, description) + Markdown instructions. The description is deliberately trigger-rich ("Use when the user asks to …") because that text is what causes the skill to be selected. Keep SKILL.md lean and push specifics into skills/<name>/reference/*.md, which SKILL.md links and the agent loads on demand (progressive disclosure).
skills/<name>/.claude-plugin/plugin.json — makes the skill an installable Claude Code plugin. The skill folder is the plugin root: SKILL.md sits at the root (not under a nested skills/ subdir), which is the supported single-skill plugin layout.
.claude-plugin/marketplace.json — one entry per skill in plugins[], each with "source": "./skills/<name>". Every skill is its own plugin, so users install only what they want.

Read the full file on GitHub · 77 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.

10d ago First seen · 77 lines · 1,099 tokens per session scan A 32b4a48f36b9

Subscribe to this mod's changes

bjorn-skills CLAUDE.md is an instructions file published in the GitHub repository Vingedal/bjorn-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,099 tokens to every session, about $0.0055 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.

Building agents Claude Code MSSQL agent-skills ai-agents claude-skills sql-server

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

bjorn-skills: Instructions file for Claude Code