claude-sdk-rs: Command for Claude Code

.claude/commands/sync-global-skills.md

sync-global-skills is a command for Claude Code from bredmond1019/claude-sdk-rs. It costs 0 tokens per session (603 once invoked), scanned B, original, Apache-2.0.

A command that copies shared agent skills from a project's .agents/skills folder into the user's global Gemini skills folder. It also checks the result with a dry run.

In plain words
What is it for?
Use it to install or refresh the template's shared skills in the global Gemini configuration.
Why use it?
It makes the same skills available to agent tools outside the current project and helps verify that the global copy matches the source.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code; mentions Gemini CLI.

This is bredmond1019/claude-sdk-rs's own configuration. It tells Claude Code how to work on claude-sdk-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-sdk-rs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/sync-global-skills.md
Clone the repo
git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

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-global-skills

README.md
[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/sync-global-skills/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/sync-global-skills)
Your own site
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/sync-global-skills"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/sync-global-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-global-skills

Your own site · 80×15
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/sync-global-skills"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/sync-global-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 603 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00000 $0.00603
Opus 5.5 $0.00000 $0.00241
Sonnet 5.5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00060

Measured 11d ago against content hash c20a7c572bba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

sync-global-skills scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

COUNT_BEFORE=$(find ~/.gemini/config/skills -name "SKILL.md" 2>/dev/null | wc -l | tr -d ' ')
.claude/commands/sync-global-skills.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sync-global-skills — Sync harness skills to global install

Installs all harness skills from .agents/skills/ into ~/.gemini/config/skills/, mirroring what /sync-global-commands does for .claude/commands/ → ~/.claude/commands/. .agents/skills/ is the vendor-neutral skill directory other agent tools (Gemini, per GEMINI.md) read; Claude Code itself reads .claude/commands/ and does not need this sync.

Instructions

  1. Guard — confirm you are in the base-template root.

    Run:

    test -f .agents/skills/README.md && echo "Guard: OK — running from base-template root" || echo "ABORT: .agents/skills/README.md not found. Run this command from the base-template root."
    
  2. Count before — record current state of ~/.gemini/config/skills/.

    Run:

    COUNT_BEFORE=$(find ~/.gemini/config/skills -name "SKILL.md" 2>/dev/null | wc -l | tr -d ' ')
    echo "Before: $COUNT_BEFORE SKILL.md files in ~/.gemini/config/skills/"
    
  3. Sync — install skills globally.

    Run:

    rsync -av --delete .agents/skills/ ~/.gemini/config/skills/
    
  4. Verify — confirm sync is complete (dry run shows nothing to do).

    Run:

    LEFTOVER=$(rsync -n --delete .agents/skills/ ~/.gemini/config/skills/ 2>&1)
    if echo "$LEFTOVER" | grep -qE '^(deleting |>f)'; then
      echo "WARN: dry run reports pending changes — sync may not be complete:"
      echo "$LEFTOVER"
    else
      echo "Verify: OK — dry run reports nothing to do"
    fi
    
  5. Report — show before/after counts.

    Run:

    COUNT_AFTER=$(find ~/.gemini/config/skills -name "SKILL.md" 2>/dev/null | wc -l | tr -d ' ')
    echo "After:  $COUNT_AFTER SKILL.md files in ~/.gemini/config/skills/"
    echo ""
    echo "Sync complete. Before: $COUNT_BEFORE  After: $COUNT_AFTER"
    

    Report the summary to the user in plain text.

Notes

  • Run this command any time harness skills are added, moved, or renamed in base-template.
  • Unlike /sync-global-commands, there is no brain/ reference directory to exclude under .agents/skills/ — the full tree syncs.

Read the full file on GitHub · 62 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 · 62 lines · 0 tokens per session scan B c20a7c572bba

Subscribe to this mod's changes

sync-global-skills is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 603 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.

Related

sync-global-skills compared with commands from other repositories

sync-global-skills next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sync-global-skillsbredmond1019/claude-sdk-rsCommand231mo agoApache-2.0B0Claude Code
wsdanielmiessler/LifeOSCommand20kyesterdayMITA0Claude Code
cancel-ralphanthropics/claude-plugins-officialCommand46kyesterdayApache-2.0A4Claude Code
engage.actionshypnguyen1209/offensive-claudeCommand41215d agoMITA11Claude Code
focusData-Wise/claude-pluginsCommand7yesterdayMITA0Claude Code
stuckData-Wise/claude-pluginsCommand7yesterdayMITA0Claude Code
quickstartorq-ai/assistant-pluginsCommand62d agoMITA23Claude Code