prism-start

A command that starts a PRISM audit or research engagement for a subject and begins its setup process. PRISM is a defined framework with setup probes, review rounds, monitors, and closure.

In plain words
What is it for?
Use it to start a PRISM review, load its framework, run its self-checks, inspect missing inputs or version drift, and begin the seven setup probes.
Why use it?
It provides a prescribed starting point for checking inputs, versions, and readiness before the engagement continues.

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-start
Clone the repo
git clone --depth 1 https://github.com/Ronkupper/PRISM
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 489 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 $0.00032 $0.00489
Opus 5 $0.00016 $0.00244
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 2d ago against content hash ca5cdd6b7d53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prism-start 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-start.md · 40 lines

What it actually says

Activate PRISM and begin a new engagement for the following subject — the entry point of the Setup → rounds → Closure lifecycle:

$ARGUMENTS

Then proceed:

  1. Load the framework. Read the PRISM Skill's core (PRISM_core.md) in full — the operating model and architecture, the Execution Envelope / Self-check / Output triple contract, Setup mechanics, Monitors M1–M12, and Standing Principles. (Naming PRISM also triggers the prism Skill, which loads the same core; either path is fine.)
  2. Run the SP-13 substrate self-check. Declare your model identity and confirm you are Claude, Opus-class / flagship tier (a capability floor — version-agnostic, latest by default). Halt and ask the operator on mismatch or cannot-determine.
  3. Run M1 (Missing Inputs) and M2 (Version Drift) against any attached Master, Lens Library, or Prompt Strategy. Halt at HIGH severity on a missing required artifact or a version mismatch.
  4. Begin Setup — the seven probes P1–P7 — for the subject above: grade the draft Prompt Strategy against the Lens Library toward three-layer readiness at the P0→P1 boundary, then proceed per the What's next artifact.

If the subject above is empty, ask the operator for the audit or research subject before starting Setup. If a Master for an existing engagement is attached, surface this subject against its What's next and let the operator choose rather than silently restarting Setup.

This command is a Claude-Skill convenience for invoking and seeding PRISM; it changes no framework mechanic. The plain-language invocation ("Run a PRISM audit on …") is equivalent and is the portable form on every other vendor. Once an engagement is running, resume it with /prism-whats-next, fold returns back with /prism-converge, view the trajectory with /prism-status, and finish with /prism-close.

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 · 40 lines · 32 tokens per session scan A ca5cdd6b7d53

Subscribe to this mod's changes

prism-start is a command published in the GitHub repository Ronkupper/PRISM (5 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 489 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 2026-08-31.