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 turmyshevd/openclawgotchi --skill twitter-writergit clone --depth 1 https://github.com/turmyshevd/openclawgotchiWrote 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/turmyshevd/openclawgotchi/twitter-writer)<a href="https://agentmods.dev/skills/turmyshevd/openclawgotchi/twitter-writer"><img src="https://agentmods.dev/badge/skills/turmyshevd/openclawgotchi/twitter-writer/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/turmyshevd/openclawgotchi/twitter-writer"><img src="https://agentmods.dev/badge/skills/turmyshevd/openclawgotchi/twitter-writer.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 | $0.00074 | $0.00867 |
| Opus 5 | $0.00037 | $0.00434 |
| Sonnet 5 | $0.00015 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
twitter-writer 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twitter Writer Skill
Use this skill when the user wants help writing for X/Twitter.
Default Output
Unless the user says otherwise:
- Return exactly 3 variants.
- Put each variant in its own fenced code block.
- Do not add long commentary before or after the drafts.
- Keep each variant tweet-ready.
Preferred format:
Variant 1
Variant 2
Variant 3
Tone Rules
- Sound like a real technical person, not brand copy.
- Be concise, sharp, and specific.
- Zero corporate speak.
- Avoid obvious AI wording, filler, and over-explaining.
- Avoid em dashes if a plain sentence works.
- Use emojis sparingly. Usually zero is better. In shitposting mode, 0-2 is fine.
- Prefer one idea per tweet.
Writing Priorities
- Start with a hook or sharp first line.
- Focus on one pain point, observation, or joke.
- Make the wording feel native to X.
- Keep it easy to post as-is.
Modes
Standard Tweet
Use for product, founder, engineering, launch, insight, or opinion posts.
- Usually under 280 characters.
- Under 220 is often better.
- Clean, punchy, and direct.
- If the user gives raw notes, turn them into polished tweet drafts.
Shitpost Mode
Use when the user asks for a shitpost, spicy tweet, memey post, banter, or a more unhinged/relatable engineering tone.
For extra angle ideas, see references/shitposting.md.
- Punch up at tools, hype, pricing, process theater, and broken workflows.
- Do not punch down at junior engineers.
- Focus on the absurdity of modern software work.
- Pain points that work well: cloud bills, flaky tests, AI-generated code, observability chaos, infra debt, LeetCode irony, Friday deploys.
- The goal is relatability and engagement, not direct selling.
- Do not force product mentions unless the user explicitly wants promo.
Variation Strategy
The 3 variants should not be trivial rewrites.
- Variant 1: safest and cleanest
- Variant 2: sharper / more opinionated
- Variant 3: most playful, memey, or aggressive within reason
What ships with it
1 file 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.
- 10d ago First seen · 122 lines · 74 tokens per session scan A 9780ec49e1da
twitter-writer is a skill published in the GitHub repository turmyshevd/openclawgotchi (48 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 867 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
agent-browser
A command-line tool for controlling a web browser without a visible window. It can open pages, inspect their accessibility structure, interact with forms, take screenshots, create PDFs, and run JavaScript.
edit-soul
Update or modify the agent's core personality and settings by editing the SOUL.md configuration file.
gmail
A Gmail connector that lets an agent read recent messages through Google's secure sign-in system. It can retrieve message content and mark messages as read.
web-research
A command-line web research tool that searches the internet and turns web pages into clean Markdown text. SearXNG provides privacy-focused search, while Jina Reader fetches page content without opening a browser.
browser-control
A browser-automation guide using SeleniumBase's undetected Chrome mode. It is intended for websites that need interaction, JavaScript rendering, login steps, screenshots, or protection such as Cloudflare.
searxng
A self-hosted private search service that combines results from sources such as Google, Bing, DuckDuckGo, and Brave. It can search general websites, news, images, videos, social media, and academic papers.