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.
npx agentmods add skills/yeedochi/openstack-mcp/openstack-profilenpx skills add YeeDochi/OpenStack-MCP --skill openstack-profilegit clone --depth 1 https://github.com/YeeDochi/OpenStack-MCPWhat 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 | $0.00070 | $0.01171 |
| Opus 5 | $0.00035 | $0.00585 |
| Sonnet 5 | $0.00014 | $0.00234 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
openstack-profile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenStack 연결 프로필 관리
이 스킬은 클라이언트의 MCP 등록(openstack-*)을 프로필 단위로 전환/관리한다.
프로필 하나 = 하나의 클라우드(메인 MCP BASE_URL) + 계정(creds).
백엔드 스크립트 선택 (OS별)
- Windows →
<skill-dir>/openstack-profile.ps1. 실행기는 버전 무관하게 있는 걸 자동 선택 —pwsh(PowerShell 7)가 있으면 그걸, 없으면 윈도우 기본 내장powershell(5.1)을 쓴다. 한 줄로:$ps = if (Get-Command pwsh -EA SilentlyContinue) { 'pwsh' } else { 'powershell' }. (pwsh하나로 박으면 PS7 미설치 PC에서CommandNotFoundException나니 박지 말 것.) - macOS/Linux →
<skill-dir>/openstack-profile.sh를bash로 실행.<skill-dir>= 이 SKILL.md가 있는 디렉터리(보통~/.claude/skills/openstack-profile).
동작
- 목록:
bash <skill-dir>/openstack-profile.sh list(Win:$ps = if (Get-Command pwsh -EA SilentlyContinue) { 'pwsh' } else { 'powershell' }; & $ps -ExecutionPolicy Bypass -File <skill-dir>\openstack-profile.ps1 list). 활성 프로필은* (active)로 표시. - 추가
add <name>: 실행하면 프롬프트로 값을 받는다. ⚠️ Claude Code의!실행은 TTY가 없어 대화형 프롬프트(read)가 건너뛰어져BASE_URL required로 죽는다. 그러니 사용자에게 "별도 터미널(실제 셸)을 열어 직접 실행"하라고 안내한다 — 그래야 프롬프트가 뜨고, 비밀도 모델 컨텍스트를 안 거친다(인자로 넘기지 말 것).!안에서 꼭 해야 하면 아래 하이브리드(env 프리필)나OPENSTACK_PROFILE_NONINTERACTIVE=1을 쓰되, 그 경우 비밀이 명령에 노출된다.- 필수(비면 재요청):
BASE_URL,OS_AUTH_URL,OS_APP_CRED_ID,OS_APP_CRED_SECRET(가려진 입력). DOMAINS(등록할 서비스 마운트 서브셋)는 프롬프트하지 않음 — 기본값=전체(compute network storage lbaas image identity observability). 서브셋이 필요할 때만 env로:DOMAINS="compute network" bash ...sh add <name>. (switch는 프로필에 DOMAINS 줄이 있으면 그대로 존중.)- 비대화형 호출(설치 스크립트 등)은
OPENSTACK_PROFILE_NONINTERACTIVE=1로 모든 프롬프트를 끔 — env로 넘긴 값만 저장. - Unix(별도 터미널에서):
bash <skill-dir>/openstack-profile.sh add <name> - Win(별도 터미널에서):
$ps = if (Get-Command pwsh -EA SilentlyContinue) { 'pwsh' } else { 'powershell' }; & $ps -ExecutionPolicy Bypass -File <skill-dir>\openstack-profile.ps1 add <name> - 하이브리드: 환경변수를 미리 세팅한 필드는 프롬프트를 건너뛴다(자동화용). 예)
BASE_URL=... OS_AUTH_URL=... OS_APP_CRED_ID=... OS_APP_CRED_SECRET=... bash <skill-dir>/openstack-profile.sh add <name>. - 기존 기반 추가:
FROM=<기존> bash <skill-dir>/openstack-profile.sh add <new>— 상속된 값은 프롬프트에서 자동 생략, 바꿀 것만 입력.
- 필수(비면 재요청):
- 전환
switch <name>:bash <skill-dir>/openstack-profile.sh switch <name>. 끝나면 사용자에게claude --continue(최근 대화 이어서) 또는claude --resume(세션 선택)로 재시작 하라고 안내 — 대화 유지하며 새 MCP 등록만 적용(그냥 재시작하면 대화가 사라짐). "지금 어느 프로필/프로젝트냐"는whoami로도 확인. - 삭제
remove <name>.
What ships with it
2 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.
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.
- yesterday First seen · 38 lines · 70 tokens per session scan A 1264e32c7049
openstack-profile is a skill published in the GitHub repository YeeDochi/OpenStack-MCP (4 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 1,171 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…