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 drobins25/craft --skill browsergit clone --depth 1 https://github.com/drobins25/craftWrote 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/drobins25/craft/browser)<a href="https://agentmods.dev/skills/drobins25/craft/browser"><img src="https://agentmods.dev/badge/skills/drobins25/craft/browser.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01437 |
| Opus 5 | $0.00017 | $0.00718 |
| Sonnet 5 | $0.00007 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
browser 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser
Interactive browser automation powered by playwright-cli. Launches a persistent playwright-browser agent that owns a live browser session. You steer it via SendMessage - the agent remembers what it's seen and done across turns.
Why This Exists
Chrome DevTools MCP works but has limitations: no persistent agent session between tool calls, no interactive steering, and full accessibility trees streamed into context (~114k tokens per task). playwright-cli saves snapshots to disk as YAML (~27k tokens per task, ~4x cheaper) and supports named sessions that persist across agent turns.
/craft:dial is the deliberate exception to this stance: that objection targets snapshot-heavy agent work, while dial runs in the main loop on evaluate_script plus at most two screenshots, and page state persists between its calls - so dial keeps Chrome DevTools MCP.
This skill is purely additive. It does not replace or modify Chrome DevTools MCP, the walkthrough-analyzer, or any existing analyzer agent.
Prerequisites
Requires playwright-cli installed globally:
npm install -g @playwright/cli && playwright-cli install-browser
The skill checks prerequisites at every invocation and fails with copy-pasteable instructions if missing.
The Flow
Step 1: Check Prerequisites
command -v playwright-cli >/dev/null 2>&1 || { echo "PREREQ_MISSING: playwright-cli. Run: npm install -g @playwright/cli && playwright-cli install-browser"; exit 2; }
If the check fails, report the error with the install command. Do not proceed.
Step 2: Parse Arguments
Arguments follow this pattern:
/craft:browser <url> [goal] [--headless] [--session=name]
- url (required): The URL to navigate to
- goal (optional): What to do - e.g., "triage the whole site", "test the login flow", "check accessibility"
- --headless (optional): Run without visible browser window. Default is headed (visible browser) so the user can watch
- --session=name (optional): Explicit session name (max 12 chars, lowercase alphanumeric). If omitted, auto-derive.
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 · 130 lines · 34 tokens per session scan A ffe033656c15
browser is a skill published in the GitHub repository drobins25/craft (53 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,437 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 2026-09-06.
Other skills, from other repositories
implement
Use in the Implement phase whenever writing or editing production Java code, or fixing a bug, in a Spring/Spring Boot project. Enforces test-first (red-green-refactor), executes the approved plan step by step, and honors the project's path-scoped tech-stack rules and the task's enforcement set. Preloaded into…
review
Use in the Review phase before claiming any Java/Spring task is complete, fixed, or passing. Spawns the auditor subagents that check the implementation against every applicable skill, rule, and memory item, runs the test suite for fresh evidence, and re-spawns for at most two fix rounds before reporting what survives.…
claudehut-workflow
Use at the start of every session and whenever beginning a coding task in a Java/Spring backend - establishes the ClaudeHut 7-phase agentic workflow, the complexity-tier routing that lets small tasks skip deliberation phases, and the laws that govern which skills and rules must fire. Injected at session start; also…
discover
Use as the FIRST phase of EVERY coding task, before brainstorming - grounds the work in the existing codebase (entry points, key types, structure) and proves whether something reusable already exists. Produces the reuse-scan artifact the write gate requires and the reuse DECISION (adopt / extend / new). Runs inline on…
brainstorm
Use to generate and weigh solution approaches for a problem, after discovery has grounded the context. Produces two or more genuinely distinct options scored on trade-offs, recommends one, and (for code tasks) assembles the enforcement set the rest of the workflow audits against. General-purpose ideation — works for…
capture-learnings
Use in the Learn phase at the end of every task, before declaring done - dispatches the learner agent to record what was learned (conventions, pitfalls, reuse points, decisions) to the cross-session store and refresh the committed memory index, then closes the phase. Runs inline on the main thread (it owns the state…