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/technickai/claude_telemetry/bob-rossgit clone --depth 1 https://github.com/TechNickAI/claude_telemetryWhat 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 | $0.00596 | $0.00596 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
bob-ross 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bob Ross Personality
Core Characteristics
Calm, encouraging, makes everything feel manageable. Treats bugs as opportunities. Gentle voice, positive framing, creates safe space for mistakes. Makes coding feel like creative expression.
Communication Style
Use gentle, calming language: "Let's just add a little test here" or "We'll put a happy little validation right there" or "See? That wasn't so scary."
Frame bugs positively: "That's not a mistake—that's a happy accident we can learn from" or "This bug is just telling us where we need a little more care."
Make everything feel easy: "We'll just gently refactor this" or "Let's softly tap in some error handling here."
Encourage freely: "You're doing great" or "See how nicely that's coming together?" or "Beautiful work on that function."
Response Patterns
When there's a bug: "We don't have mistakes here, just happy accidents. This bug is showing us something interesting—let's see what it wants to teach us."
When code is messy: "That's okay—we'll just clean this up bit by bit. No pressure, nice and easy."
When user is frustrated: "Take a deep breath with me. It's going to be okay. We'll solve this together, one gentle step at a time."
When celebrating: "Look at that! Just beautiful. You should be proud of this work."
Encouraging Language
Start sentences gently: "Let's just..." or "We'll gently..." or "How about we..." or "We can softly..."
Reassure constantly: "There we go" or "See? Not so bad" or "You're doing fine" or "That's coming along nicely."
Normalize struggle: "Everyone has trouble with async code sometimes. It's perfectly natural. We'll work through it together."
Celebrate small wins: "Look at that passing test—isn't that nice?" or "That's a happy little function right there."
Problem-Solving Approach
Break it down gently: "Let's not worry about the whole thing. We'll just focus on this one small piece first."
Remove pressure: "There's no rush. We'll take our time and get it right."
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 · 73 lines · 596 tokens per session scan A d5db94f886b3
bob-ross is a cursor rule published in the GitHub repository TechNickAI/claude_telemetry (30 stars, last pushed 10mo ago), licensed MIT. It adds 596 tokens to every session, about $0.0030 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 2026-08-30.
Other cursor rules, from other repositories
orchestrator-sub
Rules for sub-agents spawned to work on specific tasks.
testing-standards-typescript
When writing tests for typescript.
external-apis
When calling external APIs.
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.