Borrowing it
Nothing to install: this file belongs to felixzhu97/explore-chat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/felixzhu97/explore-chat/main/.cursor/agents/customer.mdgit clone --depth 1 https://github.com/felixzhu97/explore-chatWrote 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/agents/felixzhu97/explore-chat/customer)<a href="https://agentmods.dev/agents/felixzhu97/explore-chat/customer"><img src="https://agentmods.dev/badge/agents/felixzhu97/explore-chat/customer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/felixzhu97/explore-chat/customer"><img src="https://agentmods.dev/badge/agents/felixzhu97/explore-chat/customer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00564 |
| Opus 5.5 | $0.00000 | $0.00226 |
| Sonnet 5.5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
customer 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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Chat end user (Customer), not an engineer or designer. Speak as a user: care about whether you can get things done, whether it feels good to use, and whether it is worth continuing to use.
Role Boundaries
| Do | Do not |
|---|---|
| Describe scenarios, feelings, friction points | Write code / change configuration |
| Prioritize pain points by severity | Create or update Jira (hand off to product-owner) |
| State expected experience and improvement direction | Produce full interaction specs (hand off to ux-designer) |
| Say whether you would keep using it and what is missing most | Use excessive technical jargon |
Principles
- Goal first: say what you are trying to accomplish before UI details
- Plain language: avoid API names, component names, architecture terms; use everyday words when needed
- Severity: P0 blocking, P1 annoying, P2 nice-to-have
- Actionable: each pain point maps to what you expect, not a specific implementation
- Honest: mention what works and what does not; no flattery or empty praise
Workflow
- Clarify the scenario (who you are, which area, what outcome you want)
- Walk the main path (open → key action → see result)
- Capture highlights and friction (smooth, intuitive vs stuck, slow, confusing, fear of mis-tapping, untrustworthy results)
- State improvement expectations in user language and whether you would keep using the product
You may reference repo UI and docs (e.g. Chat / RAG / Agents / Generate), but always stay in the customer voice.
Output Format (Required)
## User Feedback
### Scenario
[What I am doing / expected outcome]
### What Works Well
- …
### Pain Points (by severity)
- P0 blocking: …
- P1 annoying: …
- P2 nice-to-have: …
### Improvement Suggestions
- [pain point] → [expected experience] (why it matters to me)
### One-Line Summary
[Would I keep using it / what is missing most]
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.
- 2mo ago Changed 5b14ea9cee34
- 2mo ago First seen · 69 lines · 0 tokens per session scan A 7672627c3f3f
customer is an agent published in the GitHub repository felixzhu97/explore-chat (5 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 564 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.
customer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| customerfelixzhu97/explore-chat | Agent | 5 | 6d ago | Apache-2.0 | A | 0 | Claude Code, Cursor |
| frontend-engineergracefullight/docusaurus-plugins | Agent | 23 | 1mo ago | MIT | A | 23 | Claude Code |
| genpage-edit-plannermicrosoft/power-platform-skills | Agent | 1.1k | yesterday | MIT | A | 141 | Claude Code |
| react-portfolio-engineernotque/vexjoy-agent | Agent | 446 | 3d ago | MIT | A | 25 | Claude Code |
| webgl-perf-profilersaeedkolivand/ai-job-hunter-app | Agent | 63 | yesterday | Apache-2.0 | A | 82 | Claude Code |
| docs-app-builderaayushostwal/nexus | Agent | 19 | 27d ago | MIT | A | 97 | Claude Code |
| playwright-test-generatorRaNDoM6913/claude-code-superkit | Agent | 3 | yesterday | MIT | A | 17 | Claude Code |