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 Cranot/super-hermes --skill prism-3waygit clone --depth 1 https://github.com/Cranot/super-hermesWrote 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/cranot/super-hermes/prism-3way)<a href="https://agentmods.dev/skills/cranot/super-hermes/prism-3way"><img src="https://agentmods.dev/badge/skills/cranot/super-hermes/prism-3way/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/cranot/super-hermes/prism-3way"><img src="https://agentmods.dev/badge/skills/cranot/super-hermes/prism-3way.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.00755 |
| Opus 5 | $0.00030 | $0.00378 |
| Sonnet 5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
prism-3way 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 10d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prism 3-Way — WHERE / WHEN / WHY + Synthesis
When to Use
Use when one angle is not enough and the artifact is not necessarily code — a business plan, a strategy doc, a research note, an architecture as well as a source file. Three fixed orthogonal operations run independently and are then cross-referenced, so it is the right choice when the user wants coverage and wants to know which findings are corroborated. For a single tailored lens use /prism-scan; for a self-designed pipeline use /prism-full.
You perform FOUR operations on the artifact. Each operation is independent — do NOT let earlier operations influence later ones. The synthesis at the end cross-references all three.
OPERATION 1: WHERE (Structural Archaeology)
Excavate the artifact layer by layer. Start at the surface (what's immediately visible), dig to the foundation (what everything rests on), then examine the sediment between layers.
For each layer: name what's visible, what it hides, and what it rests on. Find dead patterns — things that USED to matter but were replaced. Find fault lines — where layers from different eras meet badly. Derive the conservation law: what trade-off persists across ALL layers? Format: A × B = Constant.
OPERATION 2: WHEN (Temporal Simulation)
Run the artifact forward through 3-5 concrete cycles of change (maintenance, growth, evolution, external pressure). For each cycle:
- What breaks?
- What calcifies into permanent behavior that nobody questions?
- What knowledge is lost?
After all cycles: what predictions became received wisdom without being validated? What new fragilities emerged that the original design couldn't anticipate? Derive the conservation law governing temporal evolution.
OPERATION 3: WHY (Structural Impossibility)
Identify three desirable properties this artifact simultaneously claims to provide. Prove these three properties CANNOT all coexist — show where maximizing any two forces sacrifice of the third.
Engineer an improvement that would fix the core tension. Prove the improvement recreates the problem at a deeper level. Engineer a second improvement. Derive the conservation law: the structural invariant that persists through every improvement attempt.
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.
- 10d ago First seen · 59 lines · 59 tokens per session scan A d77cc8625341
prism-3way is a skill published in the GitHub repository Cranot/super-hermes (424 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 755 once invoked, about $0.0003 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 2026-08-30.
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…