Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Claude Setup

ASecurity

Check whether the local Claude Code CLI is installed, authenticated, and compatible, or manage the optional per-repository Stop review gate. Use for setup, command-not-found, auth, version, missing capabilities, or review-gate status/enable/disable.

8 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsrustnodegit

Works with

claude codecli

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/25/2026

$npx -y skills add sanchitmonga22/cc-for-codex --skill claude-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claude Setup?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Claude Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sanchitmonga22-claude-setup/badge)](https://www.skillsdirectory.com/skills/sanchitmonga22-claude-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: claude-setup
description: "Check whether the local Claude Code CLI is installed, authenticated, and compatible, or manage the optional per-repository Stop review gate. Use for setup, command-not-found, auth, version, missing capabilities, or review-gate status/enable/disable."
---

# Claude Setup

Use the executable bridge launcher at the sibling skill path `../claude-code/scripts/cc-for-codex`, resolved to an absolute path. Invoke it directly, never through a bare `node` lookup.

Global workflow setup is a separate, explicit local operation. From a source
checkout, preview/apply it with `node plugins/cc-for-codex/scripts/install-global-workflow.mjs --check|--apply`;
to reverse only the marked blocks, use the matching
`uninstall-global-workflow.mjs` command. The plugin manager does not run these
filesystem mutations automatically.

Run `doctor --json` first. It is read-only, makes no model request, and reports only an allowlist of auth fields. It deliberately withholds email, organization identifiers, project directories, tokens, settings, and environment variables.

Use `doctor --full` only when the basic report is insufficient; Anthropic documents `claude doctor` as a local health check.

If Claude is missing or logged out, give the user the official Claude Code installation or login instructions. Do not install, update, authenticate, create tokens, change PATH, or edit Claude settings unless the user explicitly asks for that separate mutation.

The default Opus 5.5 workflow requires Claude Code 2.1.280 or newer. `doctor`
checks that model/CLI compatibility separately from provider usage and reports
`liveModelCheck: not_performed`; it does not make a model request. The guarded
bridge also requires the reported safety and core capabilities, including
structured output, background-agent JSON plus stop control, worktrees, and
resume. If any are missing, recommend upgrading or explicitly choosing a
supported model rather than silently dropping a required flag.

Foreground `-p --worktree` delegation skips Claude's trust prompt. Before a background/non-`-p` worktree write, the user must run Claude interactively in that repository and personally accept the prompt; do not automate that consent.

For the optional Codex Stop review hook:

- `review-gate status` and `review-gate disable` are local state operations and make no model call.
- Enable only after the user explicitly accepts that every eligible Codex Stop can invoke billed Claude usage. Then run `review-gate enable --confirm-review-gate enable-billed-stop-review`.
- Explain that the gate is disabled by default and stored in the Git common directory, so linked worktrees share it.
- Remind the user that Codex separately skips plugin hooks until they inspect and trust the current hook definition through `/hooks`; changed definitions need review again.
- Explain that v0.2 reviews the full current dirty Git tree, can block on older changes, blocks on partial evidence, performs only one review per Stop cycle, and fails open with a visible warning on runtime errors.

Attribution

sanchitmonga22sanchitmonga22
View sourceSee grades on GitHubMore from sanchitmonga22 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →