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 skills add redf0x1/camofox-browser --skill dogfoodgit 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/skills/redf0x1/camofox-browser/dogfood)<a href="https://agentmods.dev/skills/redf0x1/camofox-browser/dogfood"><img src="https://agentmods.dev/badge/skills/redf0x1/camofox-browser/dogfood/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/skills/redf0x1/camofox-browser/dogfood"><img src="https://agentmods.dev/badge/skills/redf0x1/camofox-browser/dogfood.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 25 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00086 | $0.01222 |
| Opus 5 | $0.00043 | $0.00611 |
| Sonnet 5 | $0.00017 | $0.00244 |
| Haiku 4.5 | $0.00009 | $0.00122 |
Grade A, and why
dogfood 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 11d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dogfood QA Testing — camofox-browser
Systematic exploratory testing of web applications using camofox-browser's anti-detection browser automation.
When to Use
- Testing web applications for bugs, UX issues, and accessibility problems
- QA validation before release
- Exploratory testing of new features
- Cross-browser verification with Firefox/Camoufox engine
Prerequisites
- camofox-browser server running on port 9377
- Target application URL accessible
Workflow
Phase 1: Initialize Session
# Create a dedicated test session
camofox open "about:blank" --user dogfood-qa
# Start trace recording for evidence capture
camofox trace start --user dogfood-qa --screenshots --snapshots
Phase 2: Navigate & Orient
# Navigate to target application
camofox navigate "https://target-app.com" --user dogfood-qa
# Take initial snapshot to understand page structure
camofox snapshot --user dogfood-qa
# Capture annotated screenshot for visual baseline
camofox annotate --user dogfood-qa
Phase 3: Systematic Exploration
3.1 Happy Path Testing
Follow the primary user flows:
# Interact with elements using refs from snapshot
camofox click e5 --user dogfood-qa
camofox type e3 "test input" --user dogfood-qa
camofox press Enter --user dogfood-qa
# Wait for navigation/loading
camofox wait networkidle --user dogfood-qa
# Capture state after each action
camofox snapshot --user dogfood-qa
3.2 Edge Case Testing
# Test empty inputs
camofox type e3 "" --user dogfood-qa
camofox press Enter --user dogfood-qa
# Test long strings
camofox type e3 "aaaa...very long string..." --user dogfood-qa
camofox press Enter --user dogfood-qa
# Test special characters
camofox type e3 "<script>alert('xss')</script>" --user dogfood-qa
camofox press Enter --user dogfood-qa
3.3 Error Discovery
# Check for console errors after interactions
camofox errors --user dogfood-qa
# Check console output for warnings
camofox console --user dogfood-qa --type warning
# Monitor all console messages
camofox console --user dogfood-qa --limit 50
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 159 lines · 86 tokens per session scan A 3395b5c2cce2
dogfood is a skill published in the GitHub repository redf0x1/camofox-browser (389 stars, last pushed 28d ago), licensed MIT. It adds 86 tokens to every session and 1,222 once invoked, about $0.0004 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 skills, from other repositories
skill
Anti-detection browser automation MCP skill for OpenClaw agents with 47 tools for navigation, interaction, observation, extraction, downloads, profiles, sessions, and stealth web search.
mk:playwright-cli
Session-persistent browser automation via Playwright CLI — form filling, screenshots, data extraction, multi-step flows. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information across multiple requests. NOT for AI-driven…
reliability
Use when user asks to stress-test the system, validate reconnection behavior, check for race conditions, or verify end-to-end data flow integrity.
founder-mode
End-to-end product builder with founder mindset. Orchestrates 9 phases: idea evaluation → architecture → TDD → implementation → E2E → verification → analysis → GTM. Produces a launched product with README, pitch, tweet thread, and Product Hunt draft. Use when: build product, founder mode, full lifecycle, idea to…
maestro-mobile-testing
Maestro mobile E2E testing patterns for React Native/Expo apps: YAML test flows, testID selectors, adaptive auth state, optimistic update verification, GraalJS scripting, cross-platform stability, CI/CD integration, Maestro Cloud, and MCP server integration. Use when: write Maestro test, flaky mobile test, test my…
e2e-pipeline
Generate and run E2E tests for mobile and web apps. Discovers screens, states, and flows via static analysis, generates Maestro test flows with assertions, executes them, and reports pass/fail results. Use when: run e2e, test flows, e2e tests, generate tests, automated testing.