What is carbone-skill CLAUDE.md?

A developer instruction file for maintaining a Carbone skill, including publishing checks, content quality, cross-file consistency, and comparison with official Carbone documentation. Carbone is a document-generation tool.

Use it when updating or publishing the Carbone skill and when checking its references, formatters, examples, and trigger descriptions.

It helps prevent unsupported syntax, outdated claims, inconsistent version information, and examples that do not match the skill's rules.

How carboneio/carbone-skill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to carboneio/carbone-skill. 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/carboneio/carbone-skill/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/carboneio/carbone-skill

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/carboneio/carbone-skill/claude-md/github.svg)](https://agentmods.dev/instructions/carboneio/carbone-skill/claude-md)

Your own site

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

Per session 596 This file is loaded in full into every session.

When invoked 596 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	$0.00596	$0.00596
Opus 5.5	$0.00238	$0.00238
Sonnet 5.5	$0.00119	$0.00119
Haiku 4.5	$0.00060	$0.00060

Measured 2mo ago against content hash 9f6be9c81778, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

carbone-skill 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 2mo 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 · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Carbone Skill — Developer Notes

Before publishing a new version

Content quality

Are the "Read this file when…" trigger lines on every reference file accurate and up to date?
Is the skill optimised for AI agents? Concretely: no invented syntax (every formatter shown appears in references/formatters.md); anti-hallucination guard present in SKILL.md; no {{ Mustache braces; no smart quotes (' / ' / " / "); all examples conform to SKILL.md §10 Validation Checklist; trigger phrasing unambiguous
Does the skill follow the latest Claude Code skill specification? SKILL.md under 500 lines; description under the 1,536-char skill-listing cap (trigger phrases live inside description — when_to_use was merged into it in v1.6.0 so the frontmatter stays close to the six-field Agent Skills spec)

Cross-file consistency

Same claim, same value across files — version requirements (v3/v4/v5), format-support lists (DOCX/XLSX/ODT/…), formatter element/scope tables (:drop/:keep, :color, :html compat), deprecation labels, pre-release flags ({o.preReleaseFeatureIn=...}) agree across SKILL.md and every reference file
All internal cross-references resolve — every see references/X.md §Y / [label](path) points to a file and section that actually exists

Cross-check against official Carbone docs

Spot-check formatter signatures, argument order, unit lists, and version requirements against carbone.io documentation for anything new or modified in this release — drift between the skill and official docs is the most common source of incorrect AI suggestions
For deeper verification (or pre-release audits), use https://carbone.io/llms-full.txt as the canonical single-file source and diff key sections against the skill — catches drift before customers do

Versioning

Pre-release check — confirm no alpha/beta/RC tags already exist for the version you're about to bump to (gh release list -R carboneio/carbone-skill or the GitHub releases page)
CHANGELOG.md updated with all changes under the correct version (semver bump: patch = doc fixes only, minor = new patterns or rules, major = breaking changes to existing tags/syntax)
Version number bumped consistently across all four files:
- carbone/SKILL.md — metadata.version
- .claude-plugin/plugin.json — version
- .claude-plugin/marketplace.json — metadata.version and plugins[0].version

Read the full file on GitHub · 25 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.

2mo ago First seen · 25 lines · 596 tokens per session scan A 9f6be9c81778

Subscribe to this mod's changes

carbone-skill CLAUDE.md is an instructions file published in the GitHub repository carboneio/carbone-skill (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 596 tokens to every session, about $0.0024 per session on Opus 5.5. 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.

carbone-skill CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
carbone-skill CLAUDE.mdcarboneio/carbone-skill	Instructions file	6	5d ago	Apache-2.0	A	596	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	yesterday	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

carbone-skill: Instructions file for Claude Code