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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill mcp-chrome-devtoolsgit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-chrome-devtools)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-chrome-devtools"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-chrome-devtools/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-chrome-devtools"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-chrome-devtools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.03676 |
| Opus 5 | $0.00016 | $0.01838 |
| Sonnet 5 | $0.00007 | $0.00735 |
| Haiku 4.5 | $0.00003 | $0.00368 |
Grade A, and why
mcp-chrome-devtools 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 today.
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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome DevTools Orchestrator - CLI + MCP Integration
Browser debugging and automation through two complementary approaches: CLI (bdg) for speed and token efficiency, MCP for multi-tool integration.
1. WHEN TO USE
Activation Triggers
Use when:
- User mentions "browser debugging", "Chrome DevTools", "CDP" explicitly
- User asks to inspect, test, or automate browser tasks with lightweight CLI approach
- User wants screenshots, HAR files, console logs, or network inspection via terminal
- User mentions "bdg" or "browser-debugger-cli" explicitly
- User needs quick DOM queries, cookie manipulation, or JavaScript execution in browser
- User wants terminal-based browser automation with Unix pipe composability
- User needs production-ready automation scripts for CI/CD browser testing
Automatic Triggers:
- "bdg", "browser-debugger-cli" mentioned explicitly
- "lightweight browser debugging" or "quick CDP access"
- "terminal-based browser automation"
- "screenshot without Puppeteer"
When NOT to Use
Do not use for:
- Complex UI testing suites requiring sophisticated frameworks (use Puppeteer/Playwright)
- Heavy multi-step automation workflows better suited for frameworks
- Cross-browser testing (bdg supports Chrome/Chromium/Edge only)
- Visual regression testing or complex test frameworks
- When user explicitly requests Puppeteer, Playwright, or Selenium
2. SMART ROUTING
Resource Loading Levels
| Level | When to Load | Resources |
|---|---|---|
| CONDITIONAL | If intent signals match | CLI/MCP/session/troubleshooting |
| ON_DEMAND | Only on explicit request | Full diagnostics set |
| FALLBACK | Zero-score routes only | Core CDP pattern reference suggested (never auto-loaded) |
What ships with it
60 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.
- assets/utcp-chrome-devtools-manuals.md 4.9 KB
- changelog/v1.0.0.0.md 2.0 KB
- changelog/v1.0.1.0.md 1.9 KB
- changelog/v1.0.10.0.md 3.1 KB
- changelog/v1.0.11.0.md 1.9 KB
- changelog/v1.0.2.0.md 1.1 KB
- changelog/v1.0.7.0.md 1.2 KB
- changelog/v1.0.8.0.md 953 B
- examples/animation-testing.sh 5.1 KB runs code
- examples/multi-viewport-test.sh 5.6 KB runs code
- examples/performance-baseline.sh 3.3 KB runs code
- examples/README.md 9.2 KB
- feature-catalog/automation-and-performance/animation-testing.md 1.8 KB
- feature-catalog/automation-and-performance/ci-integration.md 1.7 KB
- feature-catalog/automation-and-performance/multi-viewport-test.md 1.8 KB
- feature-catalog/automation-and-performance/performance-baseline.md 1.7 KB
- feature-catalog/cli-bdg-lifecycle/install-version.md 1.7 KB
- feature-catalog/cli-bdg-lifecycle/session-start.md 1.7 KB
- feature-catalog/cli-bdg-lifecycle/session-status.md 1.6 KB
- feature-catalog/cli-bdg-lifecycle/session-stop.md 1.6 KB
- feature-catalog/console-and-network/console-logs.md 1.6 KB
- feature-catalog/console-and-network/cookie-management.md 1.7 KB
- feature-catalog/console-and-network/har-export.md 1.7 KB
- feature-catalog/dom-and-screenshot/eval-javascript.md 1.7 KB
- feature-catalog/dom-and-screenshot/query-selector.md 1.6 KB
- feature-catalog/dom-and-screenshot/screenshot-capture.md 1.7 KB
- feature-catalog/dom-and-screenshot/viewport-emulation.md 1.8 KB
- feature-catalog/feature-catalog.md 10 KB
- feature-catalog/mcp-parallel-instances/code-mode-invocation.md 2.0 KB
- feature-catalog/mcp-parallel-instances/context-isolation.md 1.8 KB
- feature-catalog/mcp-parallel-instances/dual-instance-parallel.md 1.9 KB
- feature-catalog/mcp-parallel-instances/page-management.md 1.8 KB
- feature-catalog/mcp-parallel-instances/session-cleanup.md 1.7 KB
- feature-catalog/protocol-discovery/describe-domain.md 1.6 KB
- feature-catalog/protocol-discovery/list-cdp-domains.md 1.6 KB
- feature-catalog/protocol-discovery/raw-cdp-command.md 1.8 KB
- feature-catalog/protocol-discovery/search-cdp-method.md 1.5 KB
- feature-catalog/recovery-and-troubleshooting/cleanup-leak.md 1.7 KB
- feature-catalog/recovery-and-troubleshooting/dead-session.md 1.8 KB
- feature-catalog/recovery-and-troubleshooting/missing-browser.md 1.8 KB
- feature-catalog/recovery-and-troubleshooting/port-conflict.md 1.7 KB
- feature-catalog/recovery-and-troubleshooting/sandbox-errors.md 1.7 KB
- INSTALL-GUIDE.md 37 KB
- manual-testing-playbook/cli-bdg-lifecycle/install-version.md 3.1 KB
- manual-testing-playbook/cli-bdg-lifecycle/session-start.md 3.3 KB
- manual-testing-playbook/cli-bdg-lifecycle/session-stop.md 3.7 KB
- manual-testing-playbook/cli-bdg-lifecycle/status-json.md 3.1 KB
- manual-testing-playbook/console-and-network/console-list.md 4.1 KB
- manual-testing-playbook/console-and-network/cookies-retrieval.md 4.1 KB
- manual-testing-playbook/console-and-network/har-export.md 4.1 KB
- manual-testing-playbook/dom-and-screenshot/eval-javascript.md 4.0 KB
- manual-testing-playbook/dom-and-screenshot/query-selector.md 3.8 KB
- manual-testing-playbook/dom-and-screenshot/screenshot-capture.md 4.2 KB
- manual-testing-playbook/intra-routing-recall/automation.md 5.1 KB
- manual-testing-playbook/intra-routing-recall/cli.md 5.0 KB
- manual-testing-playbook/intra-routing-recall/holdout-cli.md 5.1 KB
- manual-testing-playbook/intra-routing-recall/holdout-troubleshoot.md 6.1 KB
- manual-testing-playbook/intra-routing-recall/install.md 4.7 KB
- manual-testing-playbook/intra-routing-recall/mcp.md 4.9 KB
- manual-testing-playbook/intra-routing-recall/negative.md 6.0 KB
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.
- today Changed 1ad2f6ee6af7
- 4d ago Changed 7360a7ebb566
- 6d ago First seen · 349 lines · 33 tokens per session scan A 07590930aa13
mcp-chrome-devtools is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 3,676 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.