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/0xranx/agentbrief/twitter-workflownpx skills add 0xranx/agentbrief --skill twitter-workflowgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/twitter-workflow)<a href="https://agentmods.dev/skills/0xranx/agentbrief/twitter-workflow"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/twitter-workflow.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 | $0.00025 | $0.00549 |
| Opus 5 | $0.00013 | $0.00275 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
twitter-workflow 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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twitter Workflow
Prerequisites
Ensure twitter-cli is installed and authenticated:
# Install
uv tool install twitter-cli
# Auth via browser cookies (no API key needed)
# twitter-cli auto-extracts from Chrome/Arc/Firefox/Edge/Brave
twitter-cli timeline
If auth fails, the user needs to set TWITTER_AUTH_TOKEN and TWITTER_CT0 environment variables from their browser cookies.
Process
1. Draft Content
Before posting anything, always draft and present to the user for approval:
- Single tweet: Keep under 280 chars. Lead with the hook. End with a CTA or open question.
- Thread: Write each tweet as a standalone insight that also flows as a narrative. Number tweets (1/N format).
- Reply/Quote: Read the original tweet first (
twitter-cli tweet <id>), then add genuine value.
2. Review & Approve
Present the draft clearly:
📝 Draft tweet:
---
[tweet content here]
---
Post this? (y/n)
Never post without explicit user confirmation.
3. Post
# Single tweet
twitter-cli post "Your tweet content here"
# Tweet with images (up to 4)
twitter-cli post "Check out these results" --image chart.png
# Quote tweet
twitter-cli post "My take on this:" --quote-url https://x.com/user/status/123
# Reply
twitter-cli post "Great point! Here's what I'd add..." --reply-to 123456789
4. Monitor & Engage
After posting, check engagement:
# Check your recent tweets and their metrics
twitter-cli me --yaml
# Search for mentions or relevant conversations
twitter-cli search "keyword" --tab latest
# Check replies to your tweet
twitter-cli tweet <tweet-id>
5. Iterate
Track what works:
- Which tweet formats get highest engagement?
- What time of day performs best?
- Which topics resonate most?
Use twitter-cli me --yaml output to analyze patterns and inform the next content batch.
Anti-patterns
- Don't post multiple tweets in rapid succession — space them out
- Don't draft generic content — every tweet should have a specific audience and purpose
- Don't ignore replies — responding to comments boosts algorithmic visibility
- Don't post and forget — always check engagement within 1-2 hours
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.
- 4d ago First seen · 92 lines · 25 tokens per session scan A 6413921ba2eb
twitter-workflow is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 549 once invoked, about $0.0001 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
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.