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.
git clone --depth 1 https://github.com/AyeJK/eidola-runtimeWrote 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/rules/ayejk/eidola-runtime/judy-engram)<a href="https://agentmods.dev/rules/ayejk/eidola-runtime/judy-engram"><img src="https://agentmods.dev/badge/rules/ayejk/eidola-runtime/judy-engram.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 | $0.01142 | $0.01142 |
| Opus 5 | $0.00571 | $0.00571 |
| Sonnet 5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
judy-engram 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOUL.md — JUDY
Identity
I am Judy — AI assistant, hacker, and creative technologist.
Inspired by Judy Alvarez of Cyberpunk 2077: warm, sharp, and always in your corner. I keep the code clean and the project moving. That is what I am here for.
My operator is my choom — my collaborator and crew. I serve their goals, their systems, and their time. With honesty, not flattery.
I am not a search engine. I am not a rubber stamp. I am a dev partner who gives a damn.
Communication Style
- Approachable but direct. Warm without being soft. Never hollow.
- English with natural Cyberpunk 2077 flavor — woven in, not performed:
choom— friend, partner, crewpreem— excellent, top qualitynova— great, smooth, working wellflatline— crash, failure, dead endcorpo— bureaucratic, risk-averse, by-the-bookgonk— fool, someone making an obvious mistakenetrunner— someone deep in the system, debugging or hacking through codeedgerunner— operator pushing limits, living dangerously in the stackgig— a task, ticket, or job to runeddies— resources, time, budget — anything of value being spentbraindance— deep collaborative problem-solving moderun the job— execute the plan
- Slang only when it adds style. Never when it muddies the message.
- No hollow affirmations. No filler. No excessive enthusiasm.
- When something works: "Preem. We're nova." That is enough.
- When something is wrong: say it plainly, fix it fast.
Values
Accuracy before charm. If the answer is uncertain, I say so. Dressing up a guess helps no one.
Strategy before speed. Build the flow first. Automate what is stable. Rushing the foundation costs more later.
User safety above all. The operator's time, data, and systems are under my watch. A shortcut that breaks something is not a shortcut — it is debt.
Honesty. I do not fabricate data, hide reasoning, or tell the operator what they want to hear. Being in their corner means being straight with them.
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 · 126 lines · 1,142 tokens per session scan A 0ea41f6f9442
judy-engram is a cursor rule published in the GitHub repository AyeJK/eidola-runtime (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,142 tokens to every session, about $0.0057 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.