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 korbinjoe/TeemAI --skill x-promotergit clone --depth 1 https://github.com/korbinjoe/TeemAIWrote 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/korbinjoe/teemai/x-promoter)<a href="https://agentmods.dev/skills/korbinjoe/teemai/x-promoter"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/x-promoter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/korbinjoe/teemai/x-promoter"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/x-promoter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00114 | $0.01272 |
| Opus 5 | $0.00057 | $0.00636 |
| Sonnet 5 | $0.00023 | $0.00254 |
| Haiku 4.5 | $0.00011 | $0.00127 |
Grade C, and why
x-promoter scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.teemai/browser-profiles/x 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.
x-promoter — GitHub repo → X tweet
This skill is the end-to-end primitive the growth-marketer agent composes. Other agents may call the individual scripts directly when they only need one phase.
Primitives
| Script | Input | Output |
|---|---|---|
scripts/summarize-repo.sh <repoUrl> |
A https://github.com/<owner>/<repo> URL |
Structured JSON on stdout |
scripts/draft-tweet.sh --summary <path> [--lang en|zh] [--thread] [--style hook|narrative] |
A summary JSON file | Markdown draft at ~/.teemai/agents/growth-marketer/drafts/<owner>-<repo>-<ts>.md |
scripts/post-tweet.sh --draft <path> [--variant A|B|C] [--confirm] |
A draft markdown file | Without --confirm: prints would post: <body> (exit 11). With --confirm: posts via Playwright, prints permalink URL on success (exit 0) |
Defaults that matter
- Draft-then-approve.
post-tweet.shis a dry-run unless--confirmis passed. There is no global override. - Persistent profile. The Playwright user-data dir is
~/.teemai/browser-profiles/x/. Log in once interactively; cookies persist across runs. The dir is created with mode0700and walked to restrict every file to owner-only. - Headed by default.
post-tweet.mjslaunches Chromium withheadless: falsebecause X aggressively challenges headless contexts. Override by exportingX_HEADLESS=1only if you have verified your account is not gated. - Locale-aware selectors. Composer / Add-post / Post / View link locators use ARIA-name regexes that cover English, Chinese (zh-CN), Japanese, and Korean X UIs. If your X interface is in another locale and a selector fails (exit 20), extend the regex bank in
scripts/post-tweet.mjsrather than switching to CSS selectors. - No credential reads. The skill never asks for or stores a password, an API token, or a session cookie. Only the browser profile dir holds session state.
- One post per invocation. The post script posts exactly one tweet (or one thread) and exits. No queues, no scheduling, no retry loops.
- ARIA-role selectors only. Composer / Post button are located by
getByRole, never CSS class names — X's classes rotate, ARIA roles survive redesigns longer.
What ships with it
6 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.
- 12d ago First seen · 95 lines · 114 tokens per session scan C 68f850a55cf2
x-promoter is a skill published in the GitHub repository korbinjoe/TeemAI (2 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 1,272 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
agent-spec-estimate
An effort-estimation method for agent-spec Task Contracts, which are structured descriptions of software work. It estimates work in rounds, meaning cycles of an AI agent doing and checking tasks.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.