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 plugins/stickerdaniel/browserjack/plugin/plugin marketplace add stickerdaniel/browserjackgit clone --depth 1 https://github.com/stickerdaniel/browserjackGrade A, and why
browserjack 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "browserjack",
"displayName": "Browserjack",
"version": "0.3.0",
"description": "Use OpenAI's locally installed Codex browser runtime from Claude Code (macOS)",
"author": {
"name": "Daniel Sticker"
},
"license": "MIT",
"keywords": ["browser", "chatgpt", "mcp", "macos"],
"defaultEnabled": false
}
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 · 14 lines scan A 10c0f387a623
browserjack is a plugin published in the GitHub repository stickerdaniel/browserjack (2 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
fantasy-football-skills
Fantasy football decision-support skills for Codex and Claude Code: draft strategy, weekly start/sit, waiver wire, trade analysis, and browser-driven roster operations.
draft-strategy
Fantasy football draft decision support: tiered draft boards built from your rankings, value-based drafting adjusted for your league's roster settings, live best-available guidance, and keeper cost math.
fantasy-league-setup
League configuration via settings-page read or interview. Writes a leagues.md file to your project that every other fantasy-football-skills skill reads for scoring, roster, waiver, playoff context, and Preferred browser.
lineup-strategy
Weekly start/sit decision support and a combined weekly briefing: who to start, head-to-head player comparisons, flex decisions, and floor-vs-ceiling calls. Advice only — pairs with roster-ops to execute the change.
roster-ops
Browser-automation playbooks for executing roster moves (set lineup, submit waiver claim, propose trade) in the user's own logged-in browser session. Yahoo-first with ESPN and Sleeper variants. Never handles credentials and always pauses for explicit user confirmation before any submit or confirm click.
trade-analyzer
Fantasy football trade decision support: two-sided trade evaluation that accounts for standings and positional need, league-wide scans for complementary trade partners, and counteroffer negotiation reasoning.