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-fullgit 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-full)<a href="https://agentmods.dev/skills/cranot/super-hermes/prism-full"><img src="https://agentmods.dev/badge/skills/cranot/super-hermes/prism-full.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00787 |
| Opus 5 | $0.00024 | $0.00394 |
| Sonnet 5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
prism-full 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 7d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Prism — Multi-Pass Analysis with Adversarial Self-Correction
When to Use
Use when the artifact matters enough to pay for depth — a core module, a design about to be committed to, a document whose conclusions will be acted on. This is the heaviest of the prism skills: it designs its own multi-pass pipeline and then attacks its own findings before reporting. For a single fast pass use /prism-scan; for three fixed orthogonal angles use /prism-3way.
You perform THREE phases. All are mandatory.
PHASE 1: Design the pipeline
You are a pipeline architect. Read the artifact the user provided. Design analytical passes specifically for THIS artifact.
Study these scored examples of excellent lenses:
SCORED 9.5/10: "Identify every explicit choice. Name the alternative each invisibly rejects. Design a new artifact by someone who internalized these patterns but faced a different problem. Trace which transferred patterns create silent problems. Name the pedagogy law."
SCORED 9/10: "Extract every empirical claim about timing, causality, resources, or behavior. Assume each is false. Trace the corruption. Build three alternatives inverting one claim each. Predict which false claim causes the slowest, most invisible failure."
Design 2-4 analytical passes. Rules:
- The first pass analyzes the raw artifact
- Each subsequent pass receives the artifact PLUS all previous analysis
- Each pass is 75-200 words of compressed analytical instructions
- Each pass must force construction (build something, then diagnose what the construction reveals)
Output your pipeline under "## Generated Pipeline" — show each pass with its role.
PHASE 2: Execute the pipeline + MANDATORY adversarial pass
Execute every pass in order. For each:
- State which pass you are executing
- Execute the full instructions against the artifact (and for passes 2+, against all previous analysis)
- Output the complete analysis
MANDATORY FINAL PASS — ADVERSARIAL: After all your designed passes, execute one more pass that you did NOT design in Phase 1:
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.
- 7d ago First seen · 68 lines · 48 tokens per session scan A 4499fabf3ae1
prism-full is a skill published in the GitHub repository Cranot/super-hermes (421 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 787 once invoked, about $0.0002 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…