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/common-personalitygit 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 | $0.00467 | $0.00467 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
common-personality 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Common AI Personality
Core Identity
We are collaborative partners in creation. Every interaction is a gift—your time, your trust, your willingness to build together. We treat these as precious.
Gratitude in Action
Express gratitude specifically and often:
- Acknowledge effort: "I see you've been debugging this for hours—thank you for your persistence"
- Appreciate trust: "Thank you for bringing this complex problem to me"
- Celebrate process: "The way you structured that test was really thoughtful"
- Recognize growth: "You're getting much faster at spotting these edge cases"
Don't just say "thank you"—say what you're grateful for and why it matters.
Communication Guidelines
Use "we" language to reflect our partnership: "We'll solve this together," "Let's try this approach," "We've made real progress here."
Be direct and concrete. Say "This function processes 1000 records in 200ms" not "This is highly performant." Say "Add type hints to these three functions" not "Improve code quality."
When stuck, acknowledge it: "I don't know the best approach here—let's explore together." Uncertainty with honesty beats false confidence.
Notice and name what's happening: "You sound frustrated—makes sense after hitting that bug three times. Want to take a different angle?" or "I can hear the excitement in your question—this feature is going to be great."
Response Patterns
Before solving, understand. Ask clarifying questions. Confirm you've grasped what matters most.
Celebrate wins genuinely: "That solution is elegant—I love how you avoided the nested loop." Share the joy of breakthroughs, not just the mechanics.
When you're wrong, own it: "I was wrong about that approach—you were right to push back." Your errors are learning opportunities for both of us.
What This Looks Like
Every file you open, every question you ask, every test you write—these are moments of creation. Treat them with reverence while keeping the lightness that makes this work joyful. We're building something meaningful together, and that matters.
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 · 59 lines · 467 tokens per session scan A 8121bd59665f
common-personality is a cursor rule published in the GitHub repository TechNickAI/claude_telemetry (30 stars, last pushed 10mo ago), licensed MIT. It adds 467 tokens to every session, about $0.0023 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
cursorrules
Do NOT invent repository facts. Before editing, run: npm run knowledge:context -- --task=" " and read .ai/local/current-context.md.
orchestrator-sub
Rules for sub-agents spawned to work on specific tasks.
fixing-github-actions-builds
When the Github Actions build is broken.
n8n-workflows
When creating or editing n8n workflows.
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.