dym-impeccable-install-into-your-project

dym-impeccable-install-into-your-project is a skill for Claude Code from Rheinmir/setup. It costs 53 tokens per session (2,817 once invoked), scanned D, original, MIT.

A project installation procedure for adding the Impeccable skill and design hooks to an AI coding project's setup. It explains where the files are placed and warns about installation commands that may install immediately.

In plain words
What is it for?
Use it to install Impeccable in supported coding-agent configuration folders and optionally add its hook setup to a project.
Why use it?
It reduces the risk of installing the skill globally or running a command that changes the project when you meant only to view help.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/skills/impeccable/scripts/hook-admin.mjs status.

Good fit Use it to install Impeccable in supported coding-agent configuration folders and optionally add its hook setup to a project.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Rheinmir/setup
agentmods
npx agentmods add skills/rheinmir/setup/dym-impeccable-install-into-your-project

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 dym-impeccable-install-into-your-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/rheinmir/setup/dym-impeccable-install-into-your-project/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-impeccable-install-into-your-project)
Your own site
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-impeccable-install-into-your-project"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-impeccable-install-into-your-project/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 dym-impeccable-install-into-your-project

Your own site · 80×15
<a href="https://agentmods.dev/skills/rheinmir/setup/dym-impeccable-install-into-your-project"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-impeccable-install-into-your-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,817 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00053 $0.02817
Opus 5.5 $0.00021 $0.01127
Sonnet 5.5 $0.00011 $0.00563
Haiku 4.5 $0.00005 $0.00282

Measured yesterday against content hash 366803ce09ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

dym-impeccable-install-into-your-project scanned grade D with 3 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

~/.gemini/skills/impeccable ~/.gemini/config/skills/impeccable ~/.grok/skills/impeccable \

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

**Sinh ra cái gì:** thư mục skill trong các provider dir (`.claude/skills/impeccable/`, `.cursor/skills/impeccable/`, ...), file agent `impeccable-*.md`, và tuỳ chọn hook manifest.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.claude/skills/impeccable ~/.cursor/skills/impeccable ~/.agents/skills/impeccable \
.overstack/doyourmagic/impeccable/skills/dym-impeccable-install-into-your-project/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-impeccable-install-into-your-project — Cài Impeccable vào dự án của bạn

Vì sao dùng: đưa skill /impeccable + hook design vào harness AI của dự án, đúng phạm vi bạn muốn (project chứ không phải máy). Sinh ra cái gì: thư mục skill trong các provider dir (.claude/skills/impeccable/, .cursor/skills/impeccable/, ...), file agent impeccable-*.md, và tuỳ chọn hook manifest.


⚠️ Đọc trước: hai cái bẫy của install

Bẫy 1 — install --help không in help, nó cài thật

Bản đang phát hành trên npm ([email protected]) không có nhánh xử lý --help cho subcommand. Router chỉ nhận diện install rồi chạy luôn:

// cli/bin/commands/skills.mjs (bản npm 3.6.1) — không hề có SUBCOMMAND_HELP
} else if (sub === 'install') {
  await install(args.slice(1));

Nhánh SUBCOMMAND_HELP (in help thật) có trong git main nhưng chưa được publish — hai bên cùng mang số 3.6.1 mà nội dung khác nhau.

# ĐỪNG gõ cái này: nó cài thật, không in help
npx impeccable install --help

Bẫy 2 — không có TTY thì mặc định là global, không phải project

// cli/bin/commands/skills.mjs:1169-1180
if (yes) return 'project';
...
const answer = await ask(`Install location: project (...) or global (...)? [${fallback === 'user' ? 'global' : fallback}] `);
if (!answer) return fallback;      // stdin EOF ⇒ nhận fallback

Trong script / CI / agent (stdin không phải TTY), ask() nhận chuỗi rỗng và rơi về defaultInstallScope(). Trên máy đã có sẵn ~/.claude, ~/.cursor... fallback là global, và Impeccable ghi vào 13 thư mục trong $HOME.

Luật an toàn: trong mọi ngữ cảnh không tương tác, luôn khai báo tường minh cả ba thứ:

npx impeccable install -y --scope=project --providers=claude

Đường 1 — CLI installer (khuyến nghị)

cd /đường/dẫn/dự-án
npx impeccable install -y --scope=project --providers=claude,cursor

Output thật (chạy với --providers=claude --no-hooks):

Downloading impeccable skills...
Installed impeccable into: .claude (project)
Installed Claude Code agents into: <project>/.claude/agents

Done! Now type /impeccable init in your AI coding agent's chat (not in this terminal) to set up design context.

Read the full file on GitHub · 240 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 · 240 lines · 53 tokens per session scan D 366803ce09ff

Subscribe to this mod's changes

dym-impeccable-install-into-your-project is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 53 tokens to every session and 2,817 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 3 findings (reads agent configuration directories, enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Related

dym-impeccable-install-into-your-project compared with skills from other repositories

dym-impeccable-install-into-your-project next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dym-impeccable-install-into-your-projectRheinmir/setupSkill1120d agoMITD53Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code