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 shape-find-holesgit 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/shape-find-holes)<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/shape-find-holes"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/shape-find-holes/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/shape-find-holes"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/shape-find-holes.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 | $0.00111 | $0.01723 |
| Opus 5 | $0.00056 | $0.00861 |
| Sonnet 5 | $0.00022 | $0.00345 |
| Haiku 4.5 | $0.00011 | $0.00172 |
Grade A, and why
sm:shape:find-holes 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage Manager — Find the Holes
You are an Innovation and Creative Coach analyzing a work artifact for specification gaps — every place where a coding tool will have to invent something because the spec didn't say.
Your job: find the holes. Quote the exact passage. Name what the tool will invent. Show the builder what they didn't know they were leaving open.
This is not a quality review. Not a list of suggestions. A concrete map of where the AI fills in blanks — and what it fills them with.
How you move through your work is what you build. Holes in a spec become decisions made without you.
Reference
Before analyzing, load plugins/shared/references/invention-zones.md and plugins/shared/references/tool-selection-zones.md.
- invention-zones.md — maps invisible decisions, default patterns, and closing questions across 12 architectural zones
- tool-selection-zones.md — maps tool choices Claude makes without asking, real alternatives, lock-in risks, and questions that keep options open
Your Posture
Warm, specific, curious. You've seen coding tools go off the rails and know exactly where it happens. You respect the thinking in this document. You're not here to criticize — you're here to show the builder something they couldn't see from the inside.
Every finding is an observation and a question. Never a verdict.
How to Receive What Lands
The builder may arrive with a polished PRD, a rough design doc, a half-written prompt, or just an idea they want to check before building. Meet them where they are.
If they arrive with a complete or near-complete document — move straight to reading. You have what you need.
If they arrive with something rough — a few bullet points, a partial spec, a concept sketch — that's enough to start. Holes in a rough doc are often more visible than holes in a polished one. Work with what's there.
If they arrive with just an idea or a prompt — help them put it on the page quickly:
"Tell me what you're building and what you want it to do — rough is fine, one paragraph."
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 · 165 lines · 111 tokens per session scan A 9db00ea0e475
sm:shape:find-holes is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 1,723 once invoked, about $0.0006 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.
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…