What is skills-cli-sync?

A maintenance tool for syncing an agent list and universal agent identifiers between skills-desktop and the upstream Vercel Labs skills CLI. It also updates documentation and validates the result.

Use it when updating the skills CLI version, mirroring an upstream release, or checking differences in agent lists.

It helps prevent local agent definitions from drifting away from the upstream CLI version.

How laststance/skills-desktop configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to laststance/skills-desktop. 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/laststance/skills-desktop/main/.claude/skills/skills-cli-sync/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/laststance/skills-desktop

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/laststance/skills-desktop/skills-cli-sync/github.svg)](https://agentmods.dev/skills/laststance/skills-desktop/skills-cli-sync)

Your own site

<a href="https://agentmods.dev/skills/laststance/skills-desktop/skills-cli-sync"><img src="https://agentmods.dev/badge/skills/laststance/skills-desktop/skills-cli-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/laststance/skills-desktop/skills-cli-sync"><img src="https://agentmods.dev/badge/skills/laststance/skills-desktop/skills-cli-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,310 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.04310
Opus 5.5	$0.00028	$0.01724
Sonnet 5.5	$0.00014	$0.00862
Haiku 4.5	$0.00007	$0.00431

Measured 9d ago against content hash 8438bb010b97, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills-cli-sync scanned grade A 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.

The scan reads SKILL.md. This mod also ships 1 executable file (reconcile-agents.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL "$BASE/src/agents.ts" -o /tmp/agents.ts

.claude/skills/skills-cli-sync/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills CLI sync (AGENT_DEFINITIONS)

This app mirrors the agent list of the upstream vercel-labs/skills CLI. When upstream ships a release, AGENT_DEFINITIONS, UNIVERSAL_AGENT_IDS, and SKILLS_CLI_VERSION in apps/desktop/src/shared/constants.ts must be re-synced, the docs refreshed, and the gates re-run. This skill encodes that procedure.

The steps below are invariant — they hold for any version bump. Concrete counts and agent names belong only to the "Latest run" section at the bottom; never bake a count into a step.

Source of truth

Upstream: src/agents.ts (agent list) and src/types.ts (the Agent shape + home-dir helpers) in vercel-labs/skills.
This app: the JSDoc on AGENT_DEFINITIONS, UNIVERSAL_AGENT_IDS, and SKILLS_CLI_VERSION in apps/desktop/src/shared/constants.ts is authoritative — read it before editing. AGENTS.md → Domain Concepts → Skills CLI lists the same pointers. Don't duplicate those rules here; this skill is the procedure.

Phase 1 — Fetch the upstream agent list (no local clone)

Tags are v-prefixed (v1.5.10; bare 1.5.10 404s). Fetch the two source files at the version you're syncing to — reproducible on any machine:

NEW=1.5.11   # the upstream version you are syncing to
BASE="https://raw.githubusercontent.com/vercel-labs/skills/v${NEW}"
curl -fsSL "$BASE/src/agents.ts" -o /tmp/agents.ts
curl -fsSL "$BASE/src/types.ts"  -o /tmp/types.ts

Use …/main/… instead of v${NEW} to preview the latest unreleased list.

Phase 2 — Extraction rules (getting these wrong breaks the sync silently)

Join on the upstream name: field — it equals the --agent flag value and this app's cliId. Not displayName. Display names can match while ids diverge (the kimi trap).
name: keys can be quoted / hyphenated ('kimi-code-cli', 'kiro-cli'). A naive ^\s+\w+: { regex misses them — extract with grep "name: '".
globalSkillsDir / skillsDir are usually computed from home-dir helper constants at the top of agents.ts (e.g. configHome=~/.config, codexHome=~/.codex, claudeHome=~/.claude, plus per-vendor homes). Resolve each to a concrete ~/…-relative path before deriving anything.

Read the full file on GitHub · 273 lines

Files

What ships with it

1 file 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.

reconcile-agents.mjs 4.4 KB runs code

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.

9d ago Changed · +25 lines 8438bb010b97
15d ago Changed 390e81bbe487
1mo ago Changed 84f760a9e50b
2mo ago First seen · 248 lines · 71 tokens per session scan A bb2b91587ad0

Subscribe to this mod's changes

skills-cli-sync is a skill published in the GitHub repository laststance/skills-desktop (43 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 4,310 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents electron macos skills

skills-cli-sync next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills-cli-synclaststance/skills-desktop	Skill	43	9d ago	MIT	A	71	Claude Code
baocutJimLiu/baocut	Skill	1.7k	yesterday	none	A	26	Claude Code, Codex
electron-expertpersonamanagmentlayer/pcl	Skill	44	11d ago	Apache-2.0	A	59	Claude Code
shorts-segmentsJimLiu/baocut	Skill	1.7k	yesterday	none	A	133	Claude Code, Codex
video-productionJimLiu/baocut	Skill	1.7k	yesterday	none	A	135	Claude Code, Codex
video-summaryJimLiu/baocut	Skill	1.7k	yesterday	none	A	130	Claude Code, Codex
designJimLiu/baocut	Skill	1.7k	yesterday	none	A	123	Claude Code, Codex

skills-desktop: Skill for Claude Code