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/redf0x1/camofox-browser/040-anti-patternsgit clone --depth 1 https://github.com/redf0x1/camofox-browserWrote 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/redf0x1/camofox-browser/040-anti-patterns)<a href="https://agentmods.dev/rules/redf0x1/camofox-browser/040-anti-patterns"><img src="https://agentmods.dev/badge/rules/redf0x1/camofox-browser/040-anti-patterns.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 5.1 | $0.00463 | $0.00463 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
040-anti-patterns 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 6d 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
Anti-Patterns (Avoid These)
1) Skipping snapshot before actions
# BAD
camofox click e4
# GOOD
camofox snapshot
camofox click e4
2) Reusing refs after navigation/rerender
# BAD
camofox click e9
camofox navigate https://another-page.com
camofox click e9
# GOOD
camofox click e9
camofox navigate https://another-page.com
camofox snapshot
camofox click e3
3) Mixing userId across same tab flow
# BAD
camofox open https://x.com --user alice
camofox snapshot --user bob
# GOOD
camofox open https://x.com --user alice
camofox snapshot --user alice
4) Parsing text output in automation
# BAD
camofox get-url | awk '{print $2}'
# GOOD
camofox get-url --format json
5) Hardcoded query URLs instead of macros
# BAD
# manually composing search URL every time
# GOOD
# API macro use
# {"macro":"@google_search","query":"my query"}
6) Embedding plaintext credentials in scripts
# BAD
type e2 "my-secret-password"
# GOOD
camofox auth save profile
camofox auth load profile --inject --username-ref e2 --password-ref e3
7) Forgetting tab invalidation after display toggle
# BAD
# toggle display then keep using old tabId
# GOOD
# toggle display, then create a new tab
8) Assuming download command performs server-side direct fetch
# BAD
camofox download https://files.example.com/a.zip
# GOOD
camofox downloads --format json
# or call /tabs/:tabId/batch-download
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.
- 6d ago First seen · 90 lines · 463 tokens per session scan A 566120a0f464
040-anti-patterns is a cursor rule published in the GitHub repository redf0x1/camofox-browser (382 stars, last pushed 23d ago), licensed MIT. It adds 463 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
real-browser-mcp
Instructions for using Real Browser MCP to control the user's actual browser.
invictum-browser
Use Invictum Browser Bridge whenever the user requests IBB, IBG, Invictum Browser Bridge, or Invictum Browser Gate.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.