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/browser-macrosnpx skills add m4ttstack/fast-browser --skill browser-macrosgit 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 | $0.00025 | $0.01075 |
| Opus 5 | $0.00013 | $0.00537 |
| Sonnet 5 | $0.00005 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
browser-macros 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Macros
Use indexed Playwright macros instead of re-deriving known browser flows.
Flows before macros
Compiled flows are checked before hand-written macros: run fast-browser flows find --intent "<task>" --origin <origin> --json, and if a candidate
scores runnable: true, run it instead of reaching for a macro. See
fast-browsing's "Start with flows" section for the full contract.
fast-browser flows approve <name> is the one consent gate for a mutating
or js-step flow. It is separate from, and does not change, the per-macro
approval below: a mined macro still requires the user's explicit approval
for that individual macro.
The ## flow-runner entry in ~/.fast-browser/macros/MACROS.md documents
the replay contract itself: the success shape, the FLOW_RUNNER_FAILURE:
error shape, and the distinct SIDECAR_LOST: error shape for a lost
browser connection.
Recording a quirk with fast-browser sites quirk add also feeds live
interrupt recovery: a flow replay tries that recorded click once per step,
only after its full locator walk has missed.
Run a macro
- Read
~/.fast-browser/macros/MACROS.md. - Match the task to an entry's description and target.
- Call
browser_run_code_unsafewithfilenameset to the entry'sScript:path as an absolute path, your home directory written out in full, and the entry'sargsexactly. The runtime expands nothing: a bare or~name resolves against the browser server's own working directory and is refused by its containment check (ENOENTor "outside allowed roots"). Do not open the script and do not substitute inlinecode. - Return the macro's distilled result.
If the macro fails, use its { failedStep, error, url } result to retry
materially. After the same macro fails twice, append:
<macro-name> | <date> | <failedStep or reason>
to ~/.fast-browser/macro-failures.md, then switch to fast-browsing recovery.
Do not keep repeating the macro.
Prefer the affordances digest to a snapshot
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.
- yesterday First seen · 103 lines · 25 tokens per session scan A d501c1d7e125
browser-macros is a skill published in the GitHub repository m4ttstack/fast-browser (0 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 1,075 once invoked, about $0.0001 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-browser
Use when a live browser task requires Playwright interaction, authenticated handoff, visible UI verification, or ad-hoc page inspection.
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-cdp-server
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
surf-codebase
Navigate and modify surf-cli codebase - Chrome extension + native host for AI browser automation. Use for surf-cli code work, architecture questions, implementing browser control/CDP/accessibility/network features.
playwright-rs-usage
Procedural reference for using playwright-rs in Rust browser-automation code — object model (Browser/Context/Page/Locator), the locator!() macro, builder pattern for options, auto-wait semantics, adding the crate and installing its browsers, and how to capture / inspect traces for failure diagnosis. Use when writing…