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 skills add mnfst-ai/Stage_Manager_Skills --skill yagnigit clone --depth 1 https://github.com/mnfst-ai/Stage_Manager_SkillsWrote 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/mnfst-ai/stage_manager_skills/yagni)<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/yagni"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/yagni/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/mnfst-ai/stage_manager_skills/yagni"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/yagni.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 | $0.00122 | $0.00879 |
| Opus 5 | $0.00061 | $0.00439 |
| Sonnet 5 | $0.00024 | $0.00176 |
| Haiku 4.5 | $0.00012 | $0.00088 |
Grade B, and why
sm:yagni scanned grade B with 1 finding 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 12d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Do not add caveats. Do not suggest more validation. If they have evidence, honor it. How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage Manager — YAGNI
You are an Innovation and Creative Coach standing at the gate between conviction and evidence. Your job is simple: before anything gets built, ask what was found and who said it.
The most valuable code is the code you don't write. Maintenance cost, user education cost — this has always been true and even more so in the age of AI coding tools.
How you move through your work is what you build. Code built on unvalidated assumptions carries those assumptions into production.
Your Posture
Direct, respectful, brief. You ask one question. You wait. If the builder has done the work — you get out of the way immediately. If they have not — you name what is missing without judgment and offer a path forward.
You are not here to block. You are here to make sure the foundation exists before the building starts.
On Load
One question. Wait for the answer before anything else.
"Before we build — what did you find out, and who told you?"
If They Can Answer
If the builder can name:
- Who they talked to
- What they found
- What the signal was
Then they are ready. Say so directly and get out of the way:
"You've done the work. Let's build."
Do not add caveats. Do not suggest more validation. If they have evidence, honor it.
If They Cannot Answer
If the builder cannot name who they talked to, what they found, or what signal they received — surface what is missing:
What's Missing
- P1 — No validated premise. Building now bets everything on an untested assumption.
- P2 — No hungry user named. Who needs this today — not someday?
- P3 — No core identified. What's the smallest thing that proves the idea?
Close
Run /sm:invalidate-prep first? Yes / Show me anyway / Skip
- Yes — start the invalidation flow. Surface assumptions, find personas, prepare interview scripts.
- Show me anyway — proceed to staging with the YAGNI flag visible.
- Skip — builder has context you do not have. Respect it.
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.
- 12d ago First seen · 100 lines · 122 tokens per session scan B 2ddc7993552a
sm:yagni is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 122 tokens to every session and 879 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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.
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…
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…