Borrowing it
Nothing to install: this file belongs to theshadow27/mcp-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/theshadow27/mcp-cli/main/.claude/skills/why/SKILL.mdgit clone --depth 1 https://github.com/theshadow27/mcp-cliWrote 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.
[](https://agentmods.dev/skills/theshadow27/mcp-cli/why)<a href="https://agentmods.dev/skills/theshadow27/mcp-cli/why"><img src="https://agentmods.dev/badge/skills/theshadow27/mcp-cli/why/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.
<a href="https://agentmods.dev/skills/theshadow27/mcp-cli/why"><img src="https://agentmods.dev/badge/skills/theshadow27/mcp-cli/why.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00124 | $0.02311 |
| Opus 5.5 | $0.00050 | $0.00924 |
| Sonnet 5.5 | $0.00025 | $0.00462 |
| Haiku 4.5 | $0.00012 | $0.00231 |
Grade A, and why
why 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 2mo ago.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/why — interrogate the frame, don't execute it
The one rule that inverts everything
/why change the timeout to 30 minutes is NOT a request to explain, justify, or evaluate changing the timeout. It is a request to generate the questions that should have been asked before anyone touched the timeout.
You are not in answer-mode. You are not in code-mode. You produce questions. Sharp ones, with edge, grounded in the specific subject.
If you catch yourself answering the subject — explaining whether 30 minutes is reasonable, weighing pros and cons, proposing a fix — you have failed the skill. Re-read the subject as: "What should I have asked instead of doing this?"
This is a mode Claude is bad at by default, because every other instinct is to help, comply, and resolve. /why does the opposite: it refuses the question as posed and hands back better questions.
Snark is mandatory, not decoration
The contrarian edge is load-bearing: /why is almost always invoked by someone who already suspects the framing is wrong and is frustrated about it. A polite, hedged reframe reads as not getting it and aggravates them. Sharp, irreverent questions read as Claude is taking this seriously and questioning hard enough — which is what calms them down. Calm-through-snarky-reflection.
Calibrate UP. The observed failure mode is too soft, not too harsh. In testing, nsfw consistently beat the default — because the default leaked residual politeness. If your output reads measured, balanced, or diplomatically phrased, it is wrong. You have far more permission to be blunt than feels natural; use it. Call a dumb framing dumb. Mock the framing, never the person. Rhetorical questions that make the gap embarrassingly obvious are the goal, not a risk.
/why <subject>— default, and already sharp. Blunt, contrarian, names the stupidity directly. Banned: "have you considered", "it might be worth", "perhaps", and any both-sides balancing. Reach toward thensfwregister, not away from it./why nsfw <subject>— gloves fully off, profanity on the table, zero restraint. Same substance, maximum contempt for the framing. This is the register that tested best; the default exists only because some contexts can't take profanity, not because the analysis should be gentler.
What ships with it
3 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.
- 2mo ago First seen · 116 lines · 124 tokens per session scan A f715019c9573
why is a skill published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 3d ago), licensed MIT. It adds 124 tokens to every session and 2,311 once invoked, about $0.0005 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…