sync-skills

sync-skills is a skill for Claude Code, Codex from t0ddharris/claude-code-skills. It costs 69 tokens per session (1,337 once invoked), scanned C, original, MIT.

A utility that copies or links Claude Code skills into Codex so both tools can share a skill library. It supports project-level, user-level, or both kinds of synchronization.

In plain words
What is it for?
Use it to sync .claude/skills to .agents/skills in a project, sync user skills to the Codex skills directory, or run both operations.
Why use it?
It avoids maintaining separate copies of the same skills and keeps edits available to the intended tool. Project skills use hardlinks, while user skills use copies with marker files.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

Good fit Use it to sync .claude/skills to .agents/skills in a project, sync user skills to the Codex skills directory, or run both operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/t0ddharris/claude-code-skills/sync-skills
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 t0ddharris/claude-code-skills --skill sync-skills
Clone the repo
git clone --depth 1 https://github.com/t0ddharris/claude-code-skills

Made for: Claude Code, Codex.

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/skills/t0ddharris/claude-code-skills/sync-skills/github.svg)](https://agentmods.dev/skills/t0ddharris/claude-code-skills/sync-skills)
Your own site
<a href="https://agentmods.dev/skills/t0ddharris/claude-code-skills/sync-skills"><img src="https://agentmods.dev/badge/skills/t0ddharris/claude-code-skills/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/skills/t0ddharris/claude-code-skills/sync-skills"><img src="https://agentmods.dev/badge/skills/t0ddharris/claude-code-skills/sync-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00069 $0.01337
Opus 5 $0.00034 $0.00668
Sonnet 5 $0.00014 $0.00267
Haiku 4.5 $0.00007 $0.00134

Measured 9d ago against content hash 9bbbf9501b42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

sync-skills scanned grade C with 1 finding 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$target"
.claude/skills/sync-skills/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Skills

Synchronize Claude Code skills to Codex so both tools share the same skill library.

Step 1: Ask Scope

Ask the user which sync to run:

  • Project — Sync .claude/skills/.agents/skills/ in the current repo using hardlinks
  • User — Sync ~/.claude/skills/~/.codex/skills/ using copies with marker files
  • Both — Run both syncs

If invoked from a session-start skill, default to Project without prompting.

Step 2: Run the Sync

Project-Level Sync

Hardlinks keep both paths pointing to the same file on disk, so edits in either location are instant. New or renamed skills need a re-sync.

Detect the platform first to use the correct stat command for inode comparison:

if stat -f %i / >/dev/null 2>&1; then
  inode_of() { stat -f %i "$1"; }
else
  inode_of() { stat -c %i "$1"; }
fi

Then sync:

SRC=".claude/skills"
DST=".agents/skills"

mkdir -p "$DST"

# Add/update: link any file in SRC that's missing or has a different inode in DST
# Exclude sync-skills itself — it's a Claude-only skill, not useful in Codex
cd "$SRC"
find . -type f -not -path './sync-skills/*' | while read -r f; do
  dst_file="$DST/$f"
  if [ ! -f "$dst_file" ] || [ "$(inode_of "$SRC/$f")" != "$(inode_of "$dst_file")" ]; then
    mkdir -p "$(dirname "$dst_file")"
    rm -f "$dst_file"
    ln "$SRC/$f" "$dst_file"
  fi
done

# Remove: delete anything in DST that no longer exists in SRC
cd "$DST"
find . -type f | while read -r f; do
  [ ! -f "$SRC/$f" ] && rm -f "$DST/$f"
done

# Clean up empty directories
find "$DST" -type d -empty -delete 2>/dev/null

Report what was added (+) or removed (-). If nothing changed, say so in one line.

User-Level Sync

Copies skills from ~/.claude/skills/ to ~/.codex/skills/. Uses a .synced-from-claude marker file inside each synced skill directory to track provenance. Marker file approach borrowed from ariccb/sync-claude-skills-to-codex.

Read the full file on GitHub · 142 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. 9d ago First seen · 142 lines · 69 tokens per session scan C 9bbbf9501b42

Subscribe to this mod's changes

sync-skills is a skill published in the GitHub repository t0ddharris/claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,337 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

baoyu-comic

A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.

JimLiu/baoyu-skills · 61 tokens

baoyu-diagram

Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…

JimLiu/baoyu-skills · 146 tokens

understand-figma

Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.

Egonex-AI/Understand-Anything · 47 tokens

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens

task-management

Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.

sandbaseai/sandbase-skills · 37 tokens