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 skills/m4ttstack/fast-browser/capturing-flowsnpx skills add m4ttstack/fast-browser --skill capturing-flowsgit clone --depth 1 https://github.com/m4ttstack/fast-browserWhat 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 | $0.00048 | $0.01035 |
| Opus 5 | $0.00024 | $0.00517 |
| Sonnet 5 | $0.00010 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
capturing-flows 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capturing Flows
A recording shows what a screenshot cannot: the order things happened in.
Fast Browser records the browser session it drives to WebM and converts the
result to shareable GIFs with fast-browser gif.
Which sessions record
Recording covers the session Fast Browser drives: the real Chrome tabs attached through the extension relay, the ordinary connected setup. Only the tabs Fast Browser controls are recorded -- other tabs, windows, and profiles stay untouched, and the fast-browsing browser boundaries hold unchanged; there is no separate isolated browser to record in. Because the recording is of the user's real Chrome, everything visible in the driven tab lands in the file, which makes the PII rule below load-bearing, not theoretical.
The pipeline
-
Enable recording once:
fast-browser configure --video 1280x720The size is the recorded frame size,
<width>x<height>from 320x240 up to 3840x2160.fast-browser configure --video offturns recording back off, and either invocation touches only the video setting, never your profile, sessions, or palette. The new setting applies to sessions started after it, not to one already running. -
Record one flow per tab. Every page records into its own file, so a recording that mixes flows cannot be split afterwards. Open a fresh tab, drive exactly the flow you are demonstrating, and stop.
-
Close to finalize. The WebM is written incrementally and only becomes a valid, complete file when the tab or the session closes cleanly; a session that dies without closing its tab loses the recording. Never collect a recording from a tab that is still open; close it first.
-
Collect from the videos directory. Recordings land in
~/.fast-browser/videos/under generated names. The newest.webmthere is the recording that just finished. -
Convert with the CLI:
fast-browser gif <name>.webm --fps 8 --width 800
What ships with it
1 file 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.
- today First seen · 89 lines · 48 tokens per session scan A b584da973672
capturing-flows is a skill published in the GitHub repository m4ttstack/fast-browser (0 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 1,035 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 2026-08-31.
Other skills, from other repositories
webcmd-adapter-author
Use when writing a Webcmd adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces webcmd-oneshot / webcmd-explorer. For ad-hoc browser driving without an adapter, use webcmd-browser instead; for top-level…
webcmd-browser
Use when no deterministic Webcmd adapter command covers a live browser task requiring Playwright interaction, authenticated handoff, visible UI verification, or ad-hoc page inspection.
webcmd-usage
Use at the start of any Webcmd session. This is the top-level map of what webcmd can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can webcmd do?" or "how do I find the right command?".
webcmd-autofix
Automatically fix broken Webcmd adapters when commands fail. Load this skill when a webcmd command fails; it guides you through collecting a trace artifact, patching the adapter, retrying, and safely reporting reproducible upstream defects. Works with any AI agent.
smart-search
Use when a request needs search, research, source discovery, direct URL fetch, the first-choice Webcmd fetch path, evidence fetching, or search-capable Webcmd adapter discovery.
webcmd-sitemap-author
Use when creating or maintaining Webcmd site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.