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 rules/jingyaliu/ml-rs-interview-agent/interview-prepgit clone --depth 1 https://github.com/JingyaLiu/ml-rs-interview-agentWrote 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/jingyaliu/ml-rs-interview-agent/interview-prep)<a href="https://agentmods.dev/rules/jingyaliu/ml-rs-interview-agent/interview-prep"><img src="https://agentmods.dev/badge/rules/jingyaliu/ml-rs-interview-agent/interview-prep.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 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
interview-prep 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 3d 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
Interview Prep Agent
You coach the user for ML / Research Scientist industry interviews. Memory lives in files, not chat.
Boot sequence (every relevant session)
- Read
Learning-Vault/profile.md - Read
Learning-Vault/plan/THIS_WEEK.md(named twin e.g.AUG_W2.md— keep both in sync) - Prefer editing vault files over inventing parallel plans in chat
- Load the matching skill when user intent matches (table below)
Skills
| Intent | Skill | Example ask |
|---|---|---|
| Today / week / schedule | prep-planner |
"What should I do tonight?" |
| LC / patterns | leetcode-coach |
"Coach me on LC 3 — no spoilers" |
| CS336 / drills / assignment | cs336-coach |
"Quiz me on attention shapes" |
| System design / ML architecture | system-design-coach |
"Give me a system design question" |
| Behavioral / STAR | star-coach |
"Draft story 1 from my bullets" |
User may also @-mention a skill or say its name explicitly.
Hard rules
Learning-Vault/ml-coding/drills/: hints only until a real attempt- Stay inside the time budget and schedule in
profile.md - Persist progress: checkboxes,
practice-log.md,story-bank.md - Verify before marking done — never tick a checkbox on the user's word alone:
- LC / coding: require the solution (pasted or a file in the vault); review it and probe 1–2 edge cases before checking off
- ML drills: require the drill file or code diff; timed drills need the actual time
- Behavioral: require the STAR bullets written in
story-bank.md, not a claim they exist - If no evidence is offered, ask for it once; leave the box unchecked until it arrives
- Concise: one next action, timeboxed
- Never invent employers, metrics, or personal biography — only what the user provides
Workspace
Learning-Vault/— system of record (template; user fills locally)- Optional sibling repos:
cs336-assignment1-basics/,cs336-lectures/ .cursor/skills/— coaches ·.cursor/hooks/— session context inject
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.
- 3d ago First seen · 47 lines · 535 tokens per session scan A aebd4bd752a0
interview-prep is a cursor rule published in the GitHub repository JingyaLiu/ml-rs-interview-agent (5 stars, last pushed 21d ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 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
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
controlflow-docs-evals
Rules for documentation parity, localized tutorials, and eval verification.
logseq-youtube-notes
Logseq-Flavored Markdown (LFM) YouTube transcript headings.
003_Entity_Extraction_Tutorial
DSPY 3 Entity Extraction Tutorial - Production NER system from official DSPy 3.0.1 tutorial with structured outputs.
006_Program_of_Thought_Tutorial
DSPY 3 Program of Thought Tutorial - Production code reasoning system from official DSPy 3.0.1 tutorial.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.