skillet-sync

skillet-sync is a skill for Claude Code from skilletmd/skillet. It costs 50 tokens per session (871 once invoked), scanned A, original, Apache-2.0.

A guide to Skillet, a system that versions, publishes, shares, and syncs plain-text instructions for AI agents across tools such as Claude Code, Codex, Cursor, and Windsurf.

In plain words
What is it for?
Importing existing skills, checking sync status, uploading skills privately, publishing them publicly, and learning the main Skillet commands.
Why use it?
It explains how to keep the same reusable instructions available in multiple agent environments and how sharing differs from private syncing.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Importing existing skills, checking sync status, uploading skills privately, publishing them publicly, and learning the main Skillet commands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skilletmd/skillet/skillet-sync
Install

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.

Any agent
npx skills add skilletmd/skillet --skill skillet-sync
Clone the repo
git clone --depth 1 https://github.com/skilletmd/skillet

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 skillet-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/skilletmd/skillet/skillet-sync/github.svg)](https://agentmods.dev/skills/skilletmd/skillet/skillet-sync)
Your own site
<a href="https://agentmods.dev/skills/skilletmd/skillet/skillet-sync"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/skillet-sync/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.

agentmods 80×15 button for skillet-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/skilletmd/skillet/skillet-sync"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/skillet-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 871 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.
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 $0.00050 $0.00871
Opus 5 $0.00025 $0.00436
Sonnet 5 $0.00010 $0.00174
Haiku 4.5 $0.00005 $0.00087

Measured 11d ago against content hash 6281811f2bf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skillet-sync 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 11d 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.

skills/skillet-sync/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skillet-sync

Skillet syncs one SKILL.md to every agent runtime you use — Claude Code, Codex, OpenClaw, Cursor, Windsurf — and to anyone you share it with. This skill is the shortest path from "what is Skillet" to "my skill is everywhere."

The core idea

A SKILL.md is a plain text file that gives an AI agent context or capabilities — a writing voice, a refund policy, a code review checklist. Skillet treats these the same way npm treats packages: version them, publish them, sync them, and let people add them to their environment with one command.

The key difference from a directory: Skillet stores context that belongs to you — private state that survives every model wave. The public catalog is the distribution surface; the actual value is the private sync underneath.

First sync

# Install Skillet (no auth required for the first sync)
npx skilletmd

# Import skills you already have
skillet import ~/.claude/skills

# See what synced (scan state)
skillet scan

The first sync completes in under 60 seconds. No OAuth until you publish.

Publishing a skill

# Save to your profile, private
skillet upload --skill skill-name

# Make it public
skillet upload --skill skill-name --public

Publishing under an organization is done on skillet.md, not from the CLI.

Before publishing, Skillet runs a privacy scan to flag any PII (emails, tokens, API keys) in the skill content. Every published version is signed with your Ed25519 author key — recipients can verify the signature before the skill materializes on their machine.

Syncing to a new machine

# Link from skillet.md → Settings → Devices (pair code)
skillet connect ABCD-1234
skillet sync

# Or add a specific skill from another author
skillet add @taylor/writing-voice

# See incoming updates awaiting approval
skillet pending
skillet approve writing-voice --version 2

How runtimes receive the skill

Skillet writes each skill to the correct location for each runtime:

Runtime Location
Codex (universal baseline) ~/.agents/skills/<slug>/SKILL.md
Claude Code ~/.claude/skills/<slug>/SKILL.md
OpenClaw ~/.openclaw/skills/<slug>/SKILL.md
Hermes ~/.hermes/skills/<slug>/SKILL.md
Cursor .cursor/rules/<slug>.mdc
Devin Desktop ~/.codeium/windsurf/skills/<slug>/SKILL.md
Devin CLI ~/.config/devin/skills/<slug>/SKILL.md

Read the full file on GitHub · 90 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. 11d ago First seen · 90 lines · 50 tokens per session scan A 6281811f2bf0

Subscribe to this mod's changes

skillet-sync is a skill published in the GitHub repository skilletmd/skillet (3 stars, last pushed 11d ago), licensed Apache-2.0. It adds 50 tokens to every session and 871 once invoked, about $0.0003 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.