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/opentabs-dev/opentabs/build-pluginnpx skills add opentabs-dev/opentabs --skill build-plugingit clone --depth 1 https://github.com/opentabs-dev/opentabsWhat 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 | $0.00074 | $0.00167 |
| Opus 5 | $0.00037 | $0.00084 |
| Sonnet 5 | $0.00015 | $0.00033 |
| Haiku 4.5 | $0.00007 | $0.00017 |
Grade A, and why
build-plugin 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 2d ago.
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
IMPORTANT: This file is a stub. The actual skill content is maintained in __SKILL__.md in this same directory.
Before proceeding, you MUST read the file .Codex/skills/build-plugin/__SKILL__.md for the latest skill instructions. The content is kept separate so that updates to the skill are always picked up fresh, even if this stub was cached at the start of a session.
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.
- 2d ago First seen · 9 lines · 74 tokens per session scan A c869cc9e96f6
build-plugin is a skill published in the GitHub repository opentabs-dev/opentabs (926 stars, last pushed 8d ago), licensed MIT. It adds 74 tokens to every session and 167 once invoked, about $0.0004 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.
Other skills, from other repositories
codex-control-chrome-mcp
Use Codex Control Chrome MCP to control the user's normal Chrome profile through the Codex Chrome extension. Use when a task needs existing Chrome tabs, cookies, logged-in sessions, installed extensions, CDP commands, page inspection, navigation, screenshots, network/console events, or browser automation from an MCP…
control-chrome-bridge
Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…
x-marketer
Professional X/Twitter growth skill. Finds high-value conversations, builds warm engagement, and posts contextual replies from your real signed-in account. Supports three modes — reply-to-conversations (find pain points + reply), engage-influencers (warm up large accounts), and monitor-brand (track mentions +…
competitor-researcher
Research SaaS and AI-tool competitors in a real browser. Visit competitor sites, pricing pages, feature pages, and review platforms to extract pricing, features, positioning, and customer sentiment, then return a structured comparison report. Use when the user wants competitor analysis, market landscape research…
competitor-monitor
Monitor competitor websites for changes. Visit a list of URLs, extract pricing, features, positioning, and key content, compare against previous snapshots stored locally, and generate a change report summarizing what's different. Use when the user says "check competitors", "what changed on their site", "monitor these…
hanzi-browse
Delegates a browsing task to a sub-agent running in the USER'S OWN Chrome — the browser they have open right now, already signed into everything. Give it a task in natural language ("check my LinkedIn DMs", "post this reply on X", "test signup on localhost:3000") and watch the sub-agent with browserstatus, steer it…