cli-sync

A procedure for checking whether an Elixir software development kit stays aligned with the Claude command-line tool. It examines versions, message formats, control messages, and command options.

In plain words
What is it for?
Use it to inspect changelog changes, compare SDK structures, detect protocol or schema drift, and update the bundled command-line version.
Why use it?
It catches differences between the SDK and the separately changing command-line tool before they cause compatibility problems.

Skill for Claude CodeCodex

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/guess/claude_code/cli-sync
Any agent
npx skills add guess/claude_code --skill cli-sync
Clone the repo
git clone --depth 1 https://github.com/guess/claude_code

Made for: Claude Code, Codex.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,660 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00100 $0.01660
Opus 5 $0.00050 $0.00830
Sonnet 5 $0.00020 $0.00332
Haiku 4.5 $0.00010 $0.00166

Measured yesterday against content hash 4356da890001, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

The scan reads SKILL.md. This mod also ships 12 executable files (captured/anthropic-api-messages.d.ts, captured/python-sdk-client.py, captured/python-sdk-message-parser.py, …), 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 -sL "https://code.claude.com/docs/en/changelog.md" > .claude/skills/cli-sync/captured/docs/changelog.md
.claude/skills/cli-sync/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Sync

Synchronize the ClaudeCode Elixir SDK with the Claude CLI to detect schema changes, new options, control protocol drift, and update the bundled version.

Overview

The Claude CLI evolves independently of this SDK. This skill dispatches five parallel agents to check alignment across all layers: versions, message types, content blocks, control protocol, and CLI options. Each agent has self-contained instructions in a references/check-*.md file.

Canonical sources: The TypeScript SDK (@anthropic-ai/claude-agent-sdk) provides the SDKMessage union (message types) and SDKControl* types (control protocol). The Anthropic API SDK (@anthropic-ai/sdk) provides BetaContentBlock types. The Python SDK (claude-agent-sdk-python) provides cross-reference for options, field names, control protocol handling, and message parsing. See references/upstream-sources.md for the complete file-level mapping.

Workflow

Step 1: Check the Changelog

Before doing anything else, fetch and review the CLI changelog to understand what has changed since the last sync:

# Fetch the changelog
curl -sL "https://code.claude.com/docs/en/changelog.md" > .claude/skills/cli-sync/captured/docs/changelog.md

Read the fetched changelog and identify:

  • New CLI features, options, or flags added
  • Message type or content block changes
  • Control protocol changes
  • Breaking changes or deprecations
  • SDK-relevant behavioral changes

This gives you a high-level roadmap of what to look for in the detailed sync analysis that follows. Note the specific changes that are relevant to the SDK so you can prioritize them in the subsequent steps.

Step 2: Refresh Captured Data

Run the capture script via Bash to fetch the latest CLI version, help output, and SDK type definitions:

.claude/skills/cli-sync/scripts/capture-cli-data.sh

This fetches claude --version, claude --help, TypeScript/Python SDK types from npm/GitHub, Anthropic API types, and official documentation (CLI reference, hooks, plugins reference, TS SDK docs, Python SDK docs). Verify the script completes without errors before proceeding.

Read the full file on GitHub · 134 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. yesterday First seen · 134 lines · 100 tokens per session scan A 4356da890001

Subscribe to this mod's changes

cli-sync is a skill published in the GitHub repository guess/claude_code (96 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,660 once invoked, about $0.0005 per session on Opus 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.

Related

Other skills, from other repositories

tui-design

This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…

pass-agent/loomkin · 109 tokens

modern-css

Specialized knowledge for writing modern high-quality CSS. Trigger this skill when starting a new CSS project/file, when the user asks about new CSS features (e.g. Masonry, View Transitions, Container Queries, Scroll-driven animations), or requests refactoring of legacy styles to modern standards.

pass-agent/loomkin · 61 tokens

vault-meeting

Process a meeting transcript — extract decisions, action items, and key discussion points into structured vault entries.

pass-agent/loomkin · 23 tokens

elixir-expert

Expert in Elixir, Phoenix Framework, and OTP. Specializes in building concurrent, fault-tolerant, and real-time applications using the BEAM. Use when building Elixir applications, working with Phoenix, implementing GenServers, or designing distributed systems on the BEAM.

pass-agent/loomkin · 60 tokens

vault-groom

Audit and clean up knowledge base state — archive completed work, fix inconsistencies.

pass-agent/loomkin · 19 tokens

clack

Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.

pass-agent/loomkin · 72 tokens