A command for turning a one-time Webwright browser task into a reusable command-line tool. It identifies changeable inputs, documents them, and creates a Python script that can be run again.

Use it to automate repeatable website tasks and create scripts with arguments, documentation, defaults, and a reusable function.

It removes the need to repeat the same browser steps manually when values such as search terms, locations, dates, or filters change.

craft — Command by microsoft

Install

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.

agentmods

npx agentmods add commands/microsoft/webwright/craft

Clone the repo

git clone --depth 1 https://github.com/microsoft/Webwright

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 706 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00014	$0.00706
Opus 5	$0.00007	$0.00353
Sonnet 5	$0.00003	$0.00141
Haiku 4.5	$0.00001	$0.00071

Measured yesterday against content hash 8ef662037e41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

craft 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.

skills/webwright/commands/craft.md · 63 lines

What it actually says

You are operating as the Webwright agent in CLI tool mode. First read the SKILL.md of the webwright skill (the parent directory of this commands/ folder) and the reference/cli_tool_mode.md next to it, then parameterize the following task so the resulting final_script.py can be re-run later with different argument values:

$ARGUMENTS

Steps:

Identify parameters. Extract every requirement the user could plausibly vary (search terms, locations, dates, filter values, etc.). Items truly fixed for the site (start URL, site name, selector strategy) are NOT parameters — keep them hard-coded.
Write plan.md. Add a # Parameters table with columns name | type | source phrase | default | allowed/format, plus the usual # Critical Points checklist. Defaults must equal the concrete task values so python final_script.py (no args) reproduces the task.
Author final_script.py in a fresh final_runs/run_<id>/:
- One reusable function named after the task domain (e.g. def search_<domain>(arg_a, arg_b, ...): ...).
- Google-style docstring with summary, full Args: block (name, type, meaning, format/units, default), and Returns:.
- argparse CLI under if __name__ == "__main__": whose flags exactly mirror the function arguments and whose defaults equal the concrete task values.
- Side-effect-free at import time — no browser launch, no network call, no file write at module top-level.
- First log line after reset must be step 0 params: <name>=<value> <name>=<value> ....
- Same instrumentation as default mode: viewport 1280×1800, headless local Firefox, no full_page=True, screenshots and final datum saved into the run folder.
Reproduce the task with no arguments. Run python final_runs/run_<id>/final_script.py and confirm it succeeds end-to-end.
Import-safety smoke test. Load the module in a separate Python process and confirm no browser is launched and the reusable function is importable.
Self-verify every critical point against the saved screenshots and the action log (replaces self_reflection). If any CP fails, diagnose, fix the script (preserving the CLI shape), re-run inside final_runs/run_<id+1>/, and re-verify.
Show the user --help. End by running python final_runs/run_<id>/final_script.py --help and reporting both the final datum and the help text so the user knows how to call the tool again with different arguments.

Refer to reference/cli_tool_mode.md for the complete contract and reference/playwright_patterns.md for the Playwright skeleton.

Changes

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 · 63 lines · 14 tokens per session scan A 8ef662037e41

Subscribe to this mod's changes

craft is a command published in the GitHub repository microsoft/Webwright (5,954 stars, last pushed 28d ago), licensed MIT. It adds 14 tokens to every session and 706 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 2026-08-30.

Browser automation Planning Writing and docs

craft

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

e2e

auto-browse

research-perplexity

review

graphify

laravel-playwright