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/jmagly/aiwg/browser-resetnpx skills add jmagly/aiwg --skill browser-resetgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/browser-reset)<a href="https://agentmods.dev/skills/jmagly/aiwg/browser-reset"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/browser-reset.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00929 |
| Opus 5 | $0.00028 | $0.00464 |
| Sonnet 5 | $0.00011 | $0.00186 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
browser-reset 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Reset Skill (DRAFT)
Status: DRAFT — scaffolded from PoC. Implementation pending Inception outputs.
Purpose
Recover from misconfiguration, rotate the per-install token, switch browsers, or fully tear down. Every destructive operation gated by human-authorization.
When This Skill Applies
- User regenerated the token in the extension UI
- User switching from Chrome to Edge (or vice versa)
- User wants to fully uninstall browser-control wiring
browser-doctorreports irrecoverable state
Modes
Mode 1: Rotate token
- Show current setup (browser, token-file path, registry entry — token redacted)
- Confirm intent (
AskUserQuestion) - Walk user through extension regeneration:
- Click extension icon in target browser
- Click "Regenerate token" (UI label may vary by extension version)
- Copy new token
- Capture new token via interactive prompt
- Atomic write to
~/.config/playwright-mcp/token(mode preserved) - Update AIWG MCP registry env block:
aiwg mcp update playwright --env "PLAYWRIGHT_MCP_EXTENSION_TOKEN=<new>" - Re-inject:
aiwg mcp inject --provider <p> --servers playwright - Probe verify; report pass/fail
Mode 2: Switch browser
- Show current browser
- Detect alternatives (same logic as
browser-setup) - Confirm switch (
AskUserQuestion) - Walk user through extension install in new browser (if not already installed there)
- Capture token from the new browser's extension
- Update token file
- Update AIWG MCP registry (no path changes, just env)
- Re-inject
- Probe verify
Note: this mode does not remove the old browser's extension or token. User can do that manually; we don't touch user's other browsers without explicit authorization.
Mode 3: Tear down
- Show what will be removed (registry entry, provider injection, token file path)
- Explicit
human-authorizationgate (destructive) aiwg mcp remove playwright- Provider config: remove
playwrightfrommcpServers(we wrote it, we own removal) - Optionally delete
~/.config/playwright-mcp/token(prompt) - Optionally delete
.aiwg/browser-allowlist.yaml(prompt) - Note: AIWG never uninstalls the browser extension itself — that's a user action in the browser UI
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 · 95 lines · 55 tokens per session scan A 965bf8fb92d3
browser-reset is a skill published in the GitHub repository jmagly/aiwg (209 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 929 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
browser_visible
以可见模式启动真实浏览器窗口，适用于演示、调试或需要人工参与的场景。控制 headed/cdpPort 等启动参数。.
browser-cdp
Native CDP browser automation reference. Headless/headed Chrome control, screenshots, JS evaluation. (/browser-cdp, browser automation, cdp, scraping).
agent-browser
Headless browser automation CLI. Open, browse, interact with, and screenshot web pages. Use when: opening websites, browser-based login, web app testing, taking screenshots, UI verification.
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.