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 full-stack-skills/agent-skills --skill browser-tracegit clone --depth 1 https://github.com/full-stack-skills/agent-skillsWrote 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/full-stack-skills/agent-skills/browser-trace)<a href="https://agentmods.dev/skills/full-stack-skills/agent-skills/browser-trace"><img src="https://agentmods.dev/badge/skills/full-stack-skills/agent-skills/browser-trace/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/full-stack-skills/agent-skills/browser-trace"><img src="https://agentmods.dev/badge/skills/full-stack-skills/agent-skills/browser-trace.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 | $0.00088 | $0.03771 |
| Opus 5.5 | $0.00035 | $0.01508 |
| Sonnet 5.5 | $0.00018 | $0.00754 |
| Haiku 4.5 | $0.00009 | $0.00377 |
Grade A, and why
browser-trace 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 1mo 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.
This is a copy
100% identical to browser-trace — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Trace
Attach a second, read-only CDP client to a browser session that is already being driven by your main automation. The trace records the full DevTools firehose to NDJSON, polls for screenshots and DOM dumps in parallel, and slices everything into a directory tree that bash tools can search.
This skill does not drive pages — it only listens. Pair it with the browser skill, browse, Stagehand, Playwright, or anything else that speaks CDP.
When to use
- The user wants to debug a browser-automation run (failing form, missing element, hung navigation, JS exception).
- The user has a running automation and wants to attach a trace mid-flight without restarting it.
- The user wants to split a CDP firehose into network / console / DOM / page buckets.
- The user wants screenshots + DOM snapshots over time, joined to CDP events by timestamp.
If the user just wants to drive the browser, use the browser skill instead.
Setup check
node --version # require Node 18+
which browse || npm install -g browse
which jq || true # optional — used only for ad-hoc querying
Verify browse cdp exists:
browse --help | grep -q "^\s*cdp " || echo "browse cdp not available — update browse"
How it works
Every Chrome DevTools target accepts multiple concurrent CDP clients. Your main automation is one client; this skill adds a second one that only enables observation domains (Network, Console, Runtime, Log, Page) and never sends action commands.
The tracer has three pieces:
- Firehose:
browse cdp <target>streams every CDP event as one JSON object per line tocdp/raw.ndjson. - Sampler: a polling loop calls
browse screenshot --cdp <target> --path <file>andbrowse get html body --cdp <target>on an interval (default 2s). The helper passes--cdpwhen it samples so it can attach to the traced target from its own process; once a browse daemon session is attached to a CDP target, follow-up commands in that session do not need to repeat--cdp. - Bisector: after the run,
bisect-cdp.mjswalksraw.ndjsononce, slices it into per-bucket JSONL files keyed by CDP method, and additionally bisects per page using top-levelPage.frameNavigatedevents as boundaries.
What ships with it
13 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.
- agents/openai.yaml 363 B
- EXAMPLES.md 8.4 KB
- LICENSE.txt 1.0 KB
- package.json 91 B
- REFERENCE.md 20 KB
- scripts/bb-capture.mjs 3.7 KB runs code
- scripts/bb-finalize.mjs 3.2 KB runs code
- scripts/bisect-cdp.mjs 7.6 KB runs code
- scripts/lib.mjs 4.2 KB runs code
- scripts/query.mjs 8.6 KB runs code
- scripts/snapshot-loop.mjs 2.6 KB runs code
- scripts/start-capture.mjs 2.9 KB runs code
- scripts/stop-capture.mjs 1.5 KB runs code
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.
- 1mo ago First seen · 252 lines · 88 tokens per session scan A 4d286999b87b
browser-trace is a skill published in the GitHub repository full-stack-skills/agent-skills (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 88 tokens to every session and 3,771 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to browser-trace, differing in 0 lines, and is treated as a copy.
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).
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
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.