sync-skills

sync-skills is a command for Claude Code from charlieviettq/awesome-agent-skill. It costs 14 tokens per session (271 once invoked), scanned A, original, MIT.

Commands for synchronizing skills between Cursor’s nested format and Claude’s flat format. Cursor and Claude are coding-agent tools that can store reusable instructions in different folder layouts.

In plain words
What is it for?
Use it after editing skills to convert them between Cursor and Claude, preserve a mapping between paths, remove orphaned copies, compare which version is newer, and audit parity.
Why use it?
It prevents the two copies from drifting apart and can remove stale duplicate skill folders. Validation commands show whether both formats still match.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/convert-to-claude.py --in-repo --force --write-map --prune-orphans.

Good fit Use it after editing skills to convert them between Cursor and Claude, preserve a mapping between paths, remove orphaned copies, compare which version is newer, and audit parity.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/charlieviettq/awesome-agent-skill
agentmods
npx agentmods add commands/charlieviettq/awesome-agent-skill/sync-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.

agentmods badge for sync-skills

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/charlieviettq/awesome-agent-skill/sync-skills"><img src="https://agentmods.dev/badge/commands/charlieviettq/awesome-agent-skill/sync-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 271 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 $0.00014 $0.00271
Opus 5 $0.00007 $0.00135
Sonnet 5 $0.00003 $0.00054
Haiku 4.5 $0.00001 $0.00027

Measured 11d ago against content hash d8a4c0f0ba7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sync-skills 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.

.claude/commands/sync-skills.md · 36 lines

What it actually says

Default: Cursor → Claude

After editing .cursor/skills/:

python3 scripts/convert-to-claude.py --in-repo --force --write-map --prune-orphans
python3 scripts/validate-skills.py --parity

--prune-orphans removes stale nested trees under .claude/skills/ (e.g. duplicate knowledge-work/, voltagent-subagents/) so only flat mapped skills remain.

Recovery: Claude → Cursor

If you changed .claude/skills/<flat-name>/ and need Cursor nested paths updated:

python3 scripts/convert-to-cursor.py --in-repo --only-newer
python3 scripts/convert-to-claude.py --in-repo --force --write-map --prune-orphans
python3 scripts/validate-skills.py --parity

Use --force on convert-to-cursor to overwrite Cursor even when newer on disk.

Audit

python3 scripts/audit-skill-parity.py

Summarize convert counts, parity gaps, and whether validation passed.

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 · 36 lines · 14 tokens per session scan A d8a4c0f0ba7e

Subscribe to this mod's changes

sync-skills is a command published in the GitHub repository charlieviettq/awesome-agent-skill (25 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 271 once invoked, about $0.0001 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.