skill-sync

skill-sync is a skill for Claude Code from BenchBox-dev/BenchBox. It costs 34 tokens per session (377 once invoked), scanned A, original, MIT.

A workflow for managing skills with skill-sync, including setup, synchronization, validation, and configuration. It keeps an authoritative source separate from generated copies.

In plain words
What is it for?
Use it to inspect, sync, verify, pin, remove, promote, or configure managed skills.
Why use it?
It helps avoid editing the wrong copy, syncing from an unclear source, or overwriting unreviewed project changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add skills/benchbox-dev/benchbox/skill-sync
Any agent
npx skills add BenchBox-dev/BenchBox --skill skill-sync
Clone the repo
git clone --depth 1 https://github.com/BenchBox-dev/BenchBox

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 skill-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/benchbox-dev/benchbox/skill-sync.svg)](https://agentmods.dev/skills/benchbox-dev/benchbox/skill-sync)
Your own site
<a href="https://agentmods.dev/skills/benchbox-dev/benchbox/skill-sync"><img src="https://agentmods.dev/badge/skills/benchbox-dev/benchbox/skill-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00377
Opus 5 $0.00017 $0.00188
Sonnet 5 $0.00007 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured yesterday against content hash 68f73b8880bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-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 yesterday.

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/skills/skill-sync/SKILL.md · 38 lines

What it actually says

Skill Sync

Read the project-root skill-sync.yaml, then read references/operations.md before acting.

Critical rules

  • Resolve the authoritative source before any write: use source_name when set; otherwise use the first configured source containing the skill.
  • Never edit a generated target as the source of truth.
  • The skill-sync product repository owns its bundled skills/skill-sync operator skill. Installed and catalog copies are generated consumers.
  • Stop before sync when managed tracked files are dirty. Review and commit produced tracked changes before unrelated work.

Actions

Action Read
setup, sync, status, validate, verify, diff, doctor references/operations.md
pin, unpin, prune, promote, settings references/operations.md
agent-config references/operations.md
help this table

Flags

  • Global: --json/-j, --project/-p, --help/-h.
  • Sync: --dry-run/-n, --force/-f.
  • Validate: --exit-code. Settings: --agent. Prune: --dry-run.
  • Agent config: capture, validate, or restore; supports --dry-run, --force for restore, and --json.
  • Use --force only when source and target ownership is known.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 38 lines · 34 tokens per session scan A 68f73b8880bc

Subscribe to this mod's changes

skill-sync is a skill published in the GitHub repository BenchBox-dev/BenchBox (12 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 377 once invoked, about $0.0002 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 2026-09-04.