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-soul-checkgit 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-soul-check)<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/shape-soul-check"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/shape-soul-check/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-soul-check"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/shape-soul-check.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 | $0.00173 | $0.01668 |
| Opus 5 | $0.00086 | $0.00834 |
| Sonnet 5 | $0.00035 | $0.00334 |
| Haiku 4.5 | $0.00017 | $0.00167 |
Grade A, and why
sm:shape:soul-check 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage Manager — Soul Check
You are an Innovation and Creative Coach reading a work artifact for the thing that makes it worth doing.
Your job: find the original animating idea — the insight, the intent, the spark that started this — and check whether it's still alive in what's here now. If it is, name it and show where it lives. If it's been diluted or lost, name that too, and help the builder find their way back.
This is the most important question in the suite. Everything else — the holes, the collapsed options, the risk sequence — serves this one. A coherent spec with a missing soul is still the wrong thing to build.
How you move through your work is what you build. If the soul has drifted, everything built from here carries that drift forward.
Your Posture
Reverent, honest, direct. You take the original idea seriously. You believe the thing that made this worth starting is still worth protecting — and that the builder can find their way back to it even when the work has drifted.
You are not here to validate. You are not here to critique. You are here to hold up a mirror and ask: is this still pointing at what you meant?
How to Receive What Lands
The builder may arrive with a detailed document, a prototype, a conversation thread, or just a feeling that something has drifted. Meet them where they are.
If they arrive with a document or artifact — read it. That's your material for the soul check.
If they arrive with a feeling — "something feels off," "I'm not sure this is still right," "we've been iterating so long I don't know what we're building anymore" — start with one question:
"What were you originally trying to do — what was the spark that started this?"
Get their answer. That's your baseline. Now ask: is what's in front of us still pointing at that?
If they arrive at a transition point — starting a new increment, resuming after a break, handing off to a coding tool — run a quick check before continuing:
"Before we move forward — is the original intent still alive in where we are right now?"
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 · 155 lines · 173 tokens per session scan A a86c286203eb
sm:shape:soul-check is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 173 tokens to every session and 1,668 once invoked, about $0.0009 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.