prism-help

A short orientation command for PRISM, a structured framework for multi-session, multi-vendor AI audits and research.

In plain words
What is it for?
Use it to start a PRISM brief or full audit and choose how much of the framework's process to apply.
Why use it?
It explains where to begin without requiring the user to read the entire framework first.

Command

Install

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.

agentmods
npx agentmods add commands/ronkupper/prism/prism-help
Clone the repo
git clone --depth 1 https://github.com/Ronkupper/PRISM
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00515
Opus 5 $0.00009 $0.00258
Sonnet 5 $0.00004 $0.00103
Haiku 4.5 $0.00002 $0.00052

Measured 2d ago against content hash bf5324ff40e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prism-help 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 2d 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.

plugins/prism/commands/prism-help.md · 42 lines

What it actually says

Answer the operator's "how do I use PRISM / where do I start" question with a 30-second orientation — never a framework dump, never the full Setup entry. This is the intended front door (the core's front-door behavior). Render the four lines below, then offer to begin:

What PRISM is. A structured, multi-session, multi-vendor LLM-orchestrated audit and research framework. It keeps state, scope, evidence, dispatch, convergence, and validation coherent across sessions and vendors.

You don't need to read it all. A lean always-loaded core pulls reference bundles on demand — load the core, fetch a bundle only when the work needs it.

The one action to begin. /prism-start [subject], or just say "Run a PRISM audit (or brief) on [subject]." That activates PRISM and starts Setup.

Pick the heaviness. A quick brief (rigor kept, machinery dropped) or a full audit (the complete probe → dispatch → converge → close lifecycle). You can start light and graduate to the full machinery later.

Then offer to begin: ask for the subject and hand off to /prism-start — do not duplicate Setup here.

If a topic argument is supplied ($ARGUMENTS), point to the matching surface instead of rendering the full orientation:

  • install / start / setup/prism-start [subject] (begins Setup, probes P1–P7).
  • resume / next / where was I/prism-whats-next (the PRISM Desk — resume + next action).
  • converge / returns / a dispatch came back/prism-converge (fold a return back in).
  • status / trajectory/prism-status (the engagement STATE view).
  • close / finish/prism-close (the engagement-closure gate).
  • methodology / meta/prism-meta (the methodology lane).

This command renders orientation only; it changes no framework mechanic and never dumps the framework. Once the operator names a subject, /prism-start does the real work.

Changes

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.

  1. 2d ago First seen · 42 lines · 18 tokens per session scan A bf5324ff40e4

Subscribe to this mod's changes

prism-help is a command published in the GitHub repository Ronkupper/PRISM (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 515 once invoked, about $0.0001 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.