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/jondoescoding/jondoescoding-coding-rules/tweet-interview-processgit clone --depth 1 https://github.com/jondoescoding/jondoescoding-coding-rulesWhat 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 | $0.00000 | $0.01394 |
| Opus 5 | $0.00000 | $0.00697 |
| Sonnet 5 | $0.00000 | $0.00279 |
| Haiku 4.5 | $0.00000 | $0.00139 |
Grade A, and why
tweet-interview-process 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 yesterday.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tweet & Short-Form Content Interview Process
This rule outlines the systematic interview approach for creating viral, conversion-focused tweets and short-form content that aligns with the user's goals and audience.
Core Philosophy
Never assume what the user wants. Every piece of content should be strategically crafted through systematic questioning that reveals:
- True objectives (not surface-level goals)
- Audience psychology and pain points
- Authentic voice and positioning
- Optimal conversion pathways
3-Stage Interview Framework
Stage 1: Content Strategy Foundation (6 Core Questions)
Purpose: Establish the strategic foundation before any writing begins.
-
Primary Goal: What's the main action you want people to take after seeing this content?
- Engage with the content (likes/retweets/shares)?
- Click to see more of your work?
- Join a waitlist/community?
- Purchase a product/service?
- All of the above?
-
Audience Focus: Who specifically are you trying to reach?
- Entrepreneurs who need [specific solution]?
- Developers interested in [specific technology]?
- People who think [specific belief/assumption]?
- General audience impressed by [specific results]?
-
Key Message: What's the ONE thing you want people to remember?
- How fast you achieved something?
- That [common belief] is wrong?
- That [difficult thing] is accessible to everyone?
- The power of [specific method/tool]?
-
Tone: How do you want to come across?
- Helpful teacher sharing knowledge?
- Confident expert showing results?
- Relatable person who figured it out?
- Inspiring leader showing what's possible?
-
Hook Strategy: What should grab attention first?
- The time it took (X minutes/hours)?
- The visual result (amazing outcome)?
- The contrast (expectation vs reality)?
- A bold claim about [topic]?
-
CTA Integration: How prominent should your call-to-action be?
- Subtle mention that flows naturally?
- Strong focus as the main CTA?
- Brief teaser that creates curiosity?
- No CTA, pure value/engagement play?
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.
- yesterday First seen · 162 lines · 0 tokens per session scan A ab571fde963a
tweet-interview-process is a cursor rule published in the GitHub repository jondoescoding/jondoescoding-coding-rules (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,394 tokens. 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
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
app-router-patterns
Next.js 14+ App Router patterns — Server Components, Client Components, Route Handlers, Server Actions, and metadata API.
test-patterns
Selenium pytest test patterns — data-driven tests, fixtures, error handling, and performance checks.
testing-fundamentals
Core Cypress testing principles — selector strategy, smart waiting, and spec organization. Apply when writing or reviewing Cypress E2E tests.
new_features
Guidelines for integrating new features into the Task Master CLI.
utilities
// ✅ DO: Create focused, reusable utilities /.