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.
git 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/020-api-endpoints)<a href="https://agentmods.dev/rules/redf0x1/camofox-browser/020-api-endpoints"><img src="https://agentmods.dev/badge/rules/redf0x1/camofox-browser/020-api-endpoints/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/rules/redf0x1/camofox-browser/020-api-endpoints"><img src="https://agentmods.dev/badge/rules/redf0x1/camofox-browser/020-api-endpoints.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 | $0.00016 | $0.00672 |
| Opus 5.5 | $0.00006 | $0.00269 |
| Sonnet 5.5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
020-api-endpoints 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REST API Endpoints (Source-Verified)
Base URL: http://localhost:9377
Core (src/routes/core.ts)
| Method | Endpoint |
|---|---|
| POST | /sessions/:userId/cookies |
| GET | /tabs/:tabId/cookies |
| GET | /health |
| GET | /presets |
| POST | /tabs |
| GET | /tabs |
| POST | /tabs/:tabId/navigate |
| GET | /tabs/:tabId/snapshot |
| POST | /tabs/:tabId/wait |
| POST | /tabs/:tabId/click |
| POST | /tabs/:tabId/type |
| POST | /tabs/:tabId/press |
| POST | /tabs/:tabId/scroll |
| POST | /tabs/:tabId/scroll-element |
| POST | /tabs/:tabId/evaluate |
| POST | /tabs/:tabId/evaluate-extended |
| POST | /tabs/:tabId/back |
| POST | /tabs/:tabId/forward |
| POST | /tabs/:tabId/refresh |
| GET | /tabs/:tabId/links |
| GET | /tabs/:tabId/screenshot |
| GET | /tabs/:tabId/stats |
| DELETE | /tabs/:tabId |
| DELETE | /tabs/group/:listItemId |
| DELETE | /sessions/:userId |
| POST | /sessions/:userId/toggle-display |
| GET | /tabs/:tabId/downloads |
| GET | /users/:userId/downloads |
| GET | /downloads/:downloadId |
| GET | /downloads/:downloadId/content |
| DELETE | /downloads/:downloadId |
| POST | /tabs/:tabId/extract-resources |
| POST | /tabs/:tabId/batch-download |
| POST | /tabs/:tabId/resolve-blobs |
OpenClaw (src/routes/openclaw.ts)
| Method | Endpoint |
|---|---|
| GET | / |
| POST | /tabs/open |
| POST | /start |
| POST | /stop |
| POST | /navigate |
| GET | /snapshot |
| POST | /act |
Common Request Patterns
- Tab-targeted routes require user-scoped lookup (
tabId+userId). - Snapshot/click/type/press/scroll are intended to run in a loop with fresh refs.
navigatesupports direct URL or macro expansion (macro+query).
Auth Rules
- If
CAMOFOX_API_KEYis set, cookie import/export and evaluate routes requireAuthorization: Bearer <key>. - OpenClaw
POST /stopalways requiresx-admin-keyand compares it to configured admin key value. - If keys are unset, routes are open except OpenClaw
POST /stop, which still requiresx-admin-key.
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 First seen · 72 lines · 16 tokens per session scan A 72e0ec707f45
020-api-endpoints is a cursor rule published in the GitHub repository redf0x1/camofox-browser (435 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 672 once invoked, about $0.0001 per session on Opus 5.5. 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.
general
Contributing rules for backend.
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.