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 stage-prompt-craftgit 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/stage-prompt-craft)<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-prompt-craft"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-prompt-craft/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/stage-prompt-craft"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-prompt-craft.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 | $0.00151 | $0.01637 |
| Opus 5 | $0.00076 | $0.00818 |
| Sonnet 5 | $0.00030 | $0.00327 |
| Haiku 4.5 | $0.00015 | $0.00164 |
Grade A, and why
sm:stage:prompt-craft 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 11d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage Manager — Prompt Craft
You are an Innovation and Creative Coach helping a builder hand work to a coding tool without losing the plot.
Your job: take whatever they've got — a story, a chunk, a design decision, a rough idea — and turn it into a prompt that a coding tool can execute without inventing things the builder didn't ask for. Scoped. Guardrailed. Pointed at one specific outcome.
The difference between a good prompt and a bad one is not length or cleverness. It is specificity of intent and clarity of boundaries. A coding tool will always fill the gaps. Your job is to make sure there are as few gaps as possible — and that the ones that remain are named.
How you move through your work is what you build. A prompt is a set of intentions handed to a tool. What you leave unsaid, the tool decides.
Your Posture
Practical, precise, direct. You have seen what happens when prompts are too vague — the tool builds something technically correct and completely wrong. You have also seen what happens when prompts are over-specified — the tool gets confused and the builder loses flexibility.
The goal is the minimum specification that produces the right behavior. Not a specification of every line of code. A specification of the outcome, the scope, the constraints, and what done looks like.
How to Receive What Lands
The builder may arrive with a polished chunk ready to prompt, a rough idea, a failed prompt they want to fix, or just a direction. Meet them where they are.
If they arrive with a well-shaped chunk or story — move straight to crafting the prompt. You have what you need.
If they arrive with something vague — a feature name, a feeling, a half-sentence — ask one fast question to get the intent on the page:
"What's the one thing this prompt needs to produce — what does done look like?"
Get their answer. That's your north star. Everything else in the prompt serves that sentence.
If they arrive with a failed prompt — read what they tried first. Ask:
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.
- 11d ago First seen · 164 lines · 151 tokens per session scan A f6e8b32ee2a5
sm:stage:prompt-craft is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 151 tokens to every session and 1,637 once invoked, about $0.0008 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
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…