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 agentmods add commands/ronkupper/prism/prism-helpgit clone --depth 1 https://github.com/Ronkupper/PRISMWhat 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 | $0.00018 | $0.00515 |
| Opus 5 | $0.00009 | $0.00258 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
prism-help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Answer the operator's "how do I use PRISM / where do I start" question with a 30-second orientation — never a framework dump, never the full Setup entry. This is the intended front door (the core's front-door behavior). Render the four lines below, then offer to begin:
What PRISM is. A structured, multi-session, multi-vendor LLM-orchestrated audit and research framework. It keeps state, scope, evidence, dispatch, convergence, and validation coherent across sessions and vendors.
You don't need to read it all. A lean always-loaded core pulls reference bundles on demand — load the core, fetch a bundle only when the work needs it.
The one action to begin. /prism-start [subject], or just say "Run a PRISM
audit (or brief) on [subject]." That activates PRISM and starts Setup.
Pick the heaviness. A quick brief (rigor kept, machinery dropped) or a full audit (the complete probe → dispatch → converge → close lifecycle). You can start light and graduate to the full machinery later.
Then offer to begin: ask for the subject and hand off to /prism-start — do
not duplicate Setup here.
If a topic argument is supplied ($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.
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.
- 2d ago First seen · 42 lines · 18 tokens per session scan A bf5324ff40e4
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.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
propose
Manage parked phase proposals in the audit manifest — list them, materialize one (or all) into live phases, or drop one. Proposals are parked by /audit:init when the user declines (some of) the synthesized plan; materialization is a move, not a re-synthesis.