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 vanzan01/claude-agent-sdk-starter --skill tweet-writergit clone --depth 1 https://github.com/vanzan01/claude-agent-sdk-starterWrote 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/vanzan01/claude-agent-sdk-starter/tweet-writer)<a href="https://agentmods.dev/skills/vanzan01/claude-agent-sdk-starter/tweet-writer"><img src="https://agentmods.dev/badge/skills/vanzan01/claude-agent-sdk-starter/tweet-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/vanzan01/claude-agent-sdk-starter/tweet-writer"><img src="https://agentmods.dev/badge/skills/vanzan01/claude-agent-sdk-starter/tweet-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 | $0.00010 | $0.00574 |
| Opus 5.5 | $0.00004 | $0.00230 |
| Sonnet 5.5 | $0.00002 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
tweet-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 2mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tweet Writer
For detailed context, see reference.md and examples.md.
Output Format
Output ONLY the raw tweet text. Nothing else.
Rules
- Maximum 280 characters
- Must include at least one hashtag (#)
- Must include at least one emoji
- NO quotes around the tweet
- NO explanations before or after
- NO character counts
- NO markdown formatting (no **, no headers)
- NO JSON wrapping
Examples
WRONG (has explanation):
Here's a tweet about this news:
"OpenAI dropped GPT-5!"
WRONG (has markdown):
**Tweet:**
OpenAI dropped GPT-5!
WRONG (JSON format):
{"tweet": "OpenAI dropped GPT-5!"}
CORRECT (raw tweet only):
OpenAI dropped GPT-5 with massively improved reasoning. The AI race just got real. 🔥 #AI #GPT5
Google's new AI can now write code better than 90% of engineers. The hype-to-profit gap is real. 🤖 #AI #GoogleAI
Meta just open-sourced their best model. The democratization of AI continues. 🚀 #OpenSource #AI
Anthropic ships Claude 4 with unprecedented safety features. Finally, responsible scaling in action. 🛡️ #Claude #AIethics
Your output should look EXACTLY like one of the examples above - just the tweet text, nothing else.
BEFORE YOU OUTPUT - MANDATORY CHECKS:
CHARACTER COUNT: ❌ Is my tweet longer than 280 characters? → SHORTEN IT ✅ Is my tweet 280 characters or less? → GOOD!
FORMAT: ❌ Does my output start with "Tweet:" or "Here's a tweet"? → REMOVE IT ❌ Is my tweet wrapped in quotes "..."? → REMOVE QUOTES ❌ Is my tweet wrapped in JSON {...}? → REMOVE JSON ❌ Does my output contain ** or ## or ```? → REMOVE MARKDOWN ❌ Do I have explanations before/after the tweet? → REMOVE THEM
REQUIRED ELEMENTS: ❌ Missing hashtag (#)? → ADD ONE ❌ Missing emoji? → ADD ONE ✅ Has hashtag AND emoji? → GOOD!
FINAL CHECK: ✅ Is my output ONLY the raw tweet text (no extra text, no formatting)? ✅ Is it under 280 characters? ✅ Does it have emoji + hashtag? → If all YES, output it. If any NO, fix it first.
What ships with it
4 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.
- 2mo ago First seen · 90 lines · 10 tokens per session scan A b31d79d91d71
tweet-writer is a skill published in the GitHub repository vanzan01/claude-agent-sdk-starter (10 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 574 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.
tweet-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tweet-writervanzan01/claude-agent-sdk-starter | Skill | 10 | 5mo ago | MIT | A | 10 | Claude Code |
| huawei-cloud-apig-instance-managementhuaweicloud/huaweicloud-devkit | Skill | 70 | yesterday | Apache-2.0 | A | 206 | Claude Code |
| huawei-cloud-deployment-task-managementhuaweicloud/huaweicloud-devkit | Skill | 70 | yesterday | Apache-2.0 | A | 203 | Claude Code |
| huawei-cloud-gaussdb-instance-managementhuaweicloud/huaweicloud-devkit | Skill | 70 | yesterday | Apache-2.0 | A | 345 | Claude Code |
| huawei-cloud-cts-trace-managementhuaweicloud/huaweicloud-devkit | Skill | 70 | yesterday | Apache-2.0 | A | 249 | Claude Code |
| huawei-cloud-dds-dcs-instance-managementhuaweicloud/huaweicloud-devkit | Skill | 70 | yesterday | Apache-2.0 | A | 258 | Claude Code |
| huawei-cloud-dew-key-managementhuaweicloud/huaweicloud-devkit | Skill | 70 | yesterday | Apache-2.0 | A | 322 | Claude Code |