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 skills add skilletmd/skillet --skill skillet-syncgit clone --depth 1 https://github.com/skilletmd/skilletWrote 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/skills/skilletmd/skillet/skillet-sync)<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.
<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>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 | $0.00050 | $0.00871 |
| Opus 5 | $0.00025 | $0.00436 |
| Sonnet 5 | $0.00010 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
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.
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 |
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.
- 11d ago First seen · 90 lines · 50 tokens per session scan A 6281811f2bf0
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.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-writing-skills
Authoring discipline for new IJFW skills. Use when creating a new skill, writing a skill, making a skill that does X, or asked to add a skill. Trigger: create a new skill, write a skill, new skill, make me a skill, skill that does, /ijfw-writing-skills.