agentmods.dev

agent-skills-setup

agent-skills-setup is a skill for Claude Code, Codex from Luckycat133/skills-repo. It costs 80 tokens per session (1,176 once invoked), scanned A, original, MIT.

A local tool for moving or backing up coding-agent settings between supported tools such as Cursor, Claude Code, Codex, and Copilot. It covers skills, instructions, rules, and MCP settings while hiding values that look like secrets.

In plain words
What is it for?
Use it to detect existing settings, compare profiles, create backups, restore them, or move them between supported coding agents.
Why use it?
It avoids rebuilding your coding-agent setup when you change tools or computers. You can inspect the planned file changes before allowing them.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: mentions Claude Code; mentions Codex; built for cline.

not rated 2repo changed today A scan 80 tokens original MIT

Good fit Use it to detect existing settings, compare profiles, create backups, restore them, or move them between supported coding agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luckycat133/skills-repo/agent-skills-setup
View source ↗ Luckycat133/skills-repo clawhub.ai
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.

Any agent
npx skills add Luckycat133/skills-repo --skill agent-skills-setup
Clone the repo
git clone --depth 1 https://github.com/Luckycat133/skills-repo

Made for: Claude Code, Codex.

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 agent-skills-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/luckycat133/skills-repo/agent-skills-setup/github.svg)](https://agentmods.dev/skills/luckycat133/skills-repo/agent-skills-setup)
Your own site
<a href="https://agentmods.dev/skills/luckycat133/skills-repo/agent-skills-setup"><img src="https://agentmods.dev/badge/skills/luckycat133/skills-repo/agent-skills-setup/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 agent-skills-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/luckycat133/skills-repo/agent-skills-setup"><img src="https://agentmods.dev/badge/skills/luckycat133/skills-repo/agent-skills-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,176 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00080 $0.01176
Opus 5 $0.00040 $0.00588
Sonnet 5 $0.00016 $0.00235
Haiku 4.5 $0.00008 $0.00118

Measured today against content hash 843c36062daf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-skills-setup 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 today.

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.

skills/agent-skills-setup/SKILL.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.

Agent Skills Setup

AI IDE Context Migration across Cursor, Claude Code, Codex, Cline, Copilot, Windsurf, and Gemini CLI.

Permissions

  • shell: bundled offline scripts plus local read-only detection commands (git, version, mdfind). No downloads or binary installations.
  • env: path resolution only; credential-looking values are redacted, never copied or printed.
  • file_read: named source products, workspace tree, bundled references/; no probing of unlisted products.
  • file_write: reviewed plan targets after --yes consent; state under <workspace>/.agent-context-migration/.
  • network: denied. Every subcommand is offline; no downloads, telemetry, or remote calls.

Capabilities and authorization

  • detect, doctor, inventory, plan, snapshot, and bundle-verify read only named products/workspace; network access is forbidden. snapshot writes only its explicit bundle output.
  • A generic migration request authorizes planning only; separate explicit user approval (--yes) or explicit action verbs (apply, restore, 迁到) under --apply-safe authorize write.
  • Save the plan, review its diff/rebuild manifest, and apply that exact file. ACB restore constructs a dual-side plan binding bundle sources to destination targets, supporting replayable plans (--plan-in) with strict TOCTOU state guards.

Route

  1. Resolve both product profiles through ide-registry.md / registry-v2.json.
  2. Read only references/ides/.md and references/ides/.md.
  3. Load by need:

Execution & Scope

  • High-level: bash scripts/smart-ide-migration.sh migrate --source <src> --target <dst> --workspace . --objects all-portable --yes
  • Step-by-step: plan --output <plan.json> -> apply <plan.json> --manifest <manifest.json> --yes -> verify --manifest <manifest.json> -> rollback --manifest <manifest.json> --yes.
  • Device handoff (ACB): snapshot captures portable skills/instructions/MCP with atomic staging and 1:1 manifest bindings; bundle-verify re-checks checksums, bindings, secrets, and signatures; restore [--plan-only | --plan-in <plan> --yes] reviews then executes the dual-side plan. snapshot --all-installed writes only its explicit bundle output after detection review; bulk restore/apply requires --yes.
  • Cross-platform: %APPDATA% / %USERPROFILE% / $APPDATA resolution, platform detection, per-surface path isolation (remote hosts experimental); detect/doctor inspect offline.
  • The explicit legacy subcommand is read-only lookup (--print-path, --dry-run); legacy writes are disabled and enforced by the Python wrapper.
  • Object-type scope (exhaustive — apply writes nothing outside it):
    • Auto-migratable (ready): skills, instructions, mcp; opaque plugin package copy where both profiles declare it.
    • Draft-only, never auto-written: prompts, commands, agents, hooks, workflows. Executable surfaces have no staging writer; replayed plans marking them eligible fail closed.
    • Opt-in session transfer: handoff needs --objects handoff AND --include-session; travels only reviewed summary, git branch, selected files, and an explicit patch. Raw conversation, tokens, session state, machine paths, logs discarded.
    • Never migrated: trust state, generated memory, cloud knowledge, approvals, chat history.
  • Sensitive shared settings files are read only for the named migration's authorized MCP subobject; trust sections (never-migrate) and sibling settings never enter plans or bundles; strict secret redaction. See references/mcp-migration.md.
  • Claude Desktop app MCP in Settings → Extensions and Settings → Connectors is UI-managed; never infer or rewrite it from legacy JSON.

Read the full file on GitHub · 62 lines

Files

What ships with it

60 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. today Changed · +2 lines 843c36062daf
  2. 8d ago Changed a08297a036ab
  3. 12d ago First seen · 60 lines · 80 tokens per session scan A 51c6d19ed9f4

Subscribe to this mod's changes

agent-skills-setup is a skill published in the GitHub repository Luckycat133/skills-repo (2 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,176 once invoked, about $0.0004 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 2026-08-31.

Building agentsClaude Codeagent-skillsai-agentai-ideclawhubskills
Related

Other skills, from other repositories

edgeone-clawscan

The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque…

Tencent/AI-Infra-Guard · 236 tokens

cortex-mem-mcp

Persistent memory enhancement for AI agents. Store conversations, search memories with semantic retrieval, and recall context across sessions. Use this skill when you need to remember user preferences, past conversations, project context, or any information that should persist beyond the current session. Provides…

sopaco/cortex-mem · 72 tokens

clawhub

Search, install and manage skills from ClawdHub.

oujingzhou/openmozi · 14 tokens

quarkclouddrive

A coding-agent add-on for Quark Drive, a Chinese cloud storage service, using its command-line tool and API to manage files online.

quark-clouddrive/quarkclouddrive_offical · 162 tokens

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens