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-closegit 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 | $0.00041 | $0.00447 |
| Opus 5 | $0.00020 | $0.00224 |
| Sonnet 5 | $0.00008 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
prism-close 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
Close the active PRISM engagement — run the Engagement-closure gate and hand over clean deliverables.
Optional Master pointer or closing focus (may be empty):
$ARGUMENTS
Then proceed:
- Locate the Master. Use an attached Master, the one in this project/repo,
or the pointer above. If none can be found, run the SP-1 / missing-handoff
recovery protocol in
PRISM_core.md— do not regenerate the Master from memory. - Load the framework if it is not already active: read
PRISM_core.md(the Engagement-closure gate, §6.7, lives in the core). - Run the closure gate — the three-layer close sweep. Verify everything dispatched has returned and converged, open Monitors are cleared, and What's next holds no pending work. Run the reconcile-at-close checklist. If the sweep finds unfinished work, halt and surface it — do not close over a gap.
- Produce the deliverables. Fetch
reference/report-architecture.mdand build the comprehensive plain-language report (the report skeleton + craft conventions); when the decision turns on numbers, add the interactive workbook cockpit so the audience can drive the model; apply the presentation house-style. For an external handoff, followreference/external-share.md. - Record closure in the Master and write a terminal What's next that marks the engagement closed.
This command is a Claude-Skill convenience for the closure phase; it changes no framework mechanic. Saying "close this engagement" in plain language is equivalent, and is the portable form on every other vendor.
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 · 38 lines · 41 tokens per session scan A 645c2470ad59
prism-close is a command published in the GitHub repository Ronkupper/PRISM (5 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 447 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.
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.