Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/carboneio/carbone-skill/claude-mdgit clone --depth 1 https://github.com/carboneio/carbone-skillWrote 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.
[](https://agentmods.dev/instructions/carboneio/carbone-skill/claude-md)<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="Measured on agentmods" height="20"></a>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 | $0.00596 | $0.00596 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
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 5d 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.
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 inSKILL.md; no{{Mustache braces; no smart quotes ('/'/"/"); all examples conform toSKILL.md§10 Validation Checklist; trigger phrasing unambiguous - Does the skill follow the latest Claude Code skill specification?
SKILL.mdunder 500 lines;descriptionunder the 1,536-char skill-listing cap (trigger phrases live insidedescription—when_to_usewas 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,:htmlcompat), deprecation labels, pre-release flags ({o.preReleaseFeatureIn=...}) agree acrossSKILL.mdand 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.txtas 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-skillor the GitHub releases page) -
CHANGELOG.mdupdated 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.versionandplugins[0].version
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.
- 5d ago First seen · 25 lines · 596 tokens per session scan A 9f6be9c81778
carbone-skill CLAUDE.md is an instructions file published in the GitHub repository carboneio/carbone-skill (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 596 tokens to every session, about $0.0030 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.