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 notforyou23/home23 --skill xgit clone --depth 1 https://github.com/notforyou23/home23Wrote 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/notforyou23/home23/x)<a href="https://agentmods.dev/skills/notforyou23/home23/x"><img src="https://agentmods.dev/badge/skills/notforyou23/home23/x.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01230 |
| Opus 5 | $0.00016 | $0.00615 |
| Sonnet 5 | $0.00007 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
X 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 8d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X
Use this skill for direct X/Twitter work. It is the canonical Home23 interface for X: the logged-in bird browser session is the default for reads, search, posting, and replies. Use the official API only with explicit backend:"api"; configured credentials never select metered API access automatically. Do not use ad hoc shell snippets for normal X work.
When to use
Use x when the task is:
- reading a tweet or thread from a URL
- searching X for live conversation
- checking timeline or mentions
- posting or replying on X
Actions
timeline
Fetches both Following and For You feeds and writes a JSON snapshot into the agent workspace.
Input:
{
"count": 20
}
read
Reads a specific tweet by URL or ID.
Input:
{
"url": "https://x.com/user/status/123"
}
search
Searches X and optionally saves the raw JSON result.
Input:
{
"query": "home23",
"count": 10
}
mentions
Checks mentions for the logged-in account or a specific handle.
post
Posts a tweet. Use only when the user explicitly wants X activity.
Input:
{
"text": "short tweet text",
"media": ["/absolute/path/to/image.png"],
"alt": ["optional alt text"],
"confirm": true
}
Generated-image safe path:
{
"text": "short tweet text",
"generatedImage": "latest",
"requireMedia": true,
"requireGeneratedImage": true,
"alt": ["optional alt text"],
"confirm": true
}
delete
Deletes a tweet owned by the authenticated account. Use only for explicit cleanup/testing.
Input:
{
"tweetId": "123",
"confirm": true
}
reply
Replies to a tweet by URL or ID.
Input:
{
"url": "https://x.com/user/status/123",
"text": "reply text",
"confirm": true
}
Can also attach generated media safely with generatedImage:"latest", requireMedia:true, and requireGeneratedImage:true.
Gotchas
post,reply, anddeleterequireconfirm: trueon every backend. The skill blocks write/delete actions without it.birdis the default backend. Passbackend:"api"only when you specifically need official API behavior and accept X API charges.- For normal Home23 agent work, this skill is the only approved write path for X. Do not call
birddirectly for posting/replying unless you are debugging this skill or the user explicitly asks for raw CLI diagnostics. - Use
x-researchfor read-only target discovery, discourse scans, profiles, and thread follow-up. Come back toxonly for authenticated account actions. - When doing outreach, prefer a reply queue first: candidate URL, why it fits, draft in the user's voice, include-link yes/no, priority, and posted/skipped/failed state. Avoid repeated repo-link replies that look spammy.
- Official API write/media/delete actions require OAuth 1.0a user-context credentials at
secrets.skills.x.apiKey,apiSecret,accessToken, andaccessTokenSecret. Image media uses the v1.1 chunked upload flow (INIT/APPEND/FINALIZE) before v2 tweet creation. - For "generate an image and post it" workflows, use
generatedImage:"latest"plusrequireMedia:trueandrequireGeneratedImage:true. This resolves the newest receipt fromworkspace/media/generated-imagesand refuses screenshots/random PNGs. birdmust have working browser cookies for timeline/mentions or explicitbackend:"bird"fallback. If X auth is stale, those calls will fail cleanly.- This skill is for X itself. If you just need web content from an X link,
browser-automationmay still be better.
What ships with it
3 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.
- 8d ago First seen · 157 lines · 33 tokens per session scan A b11c603a04d8
X is a skill published in the GitHub repository notforyou23/home23 (11 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 1,230 once invoked, about $0.0002 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
Read and post on X/Twitter from the CLI - fetch tweets, timelines, and search; post tweets, replies, threads, and media. Cookie-based auth via twikit, bootstrapped from the local Dia browser session, secrets stored in gopass. Auto-falls back to agent-browser when twikit hits internal-API drift or X's "looks automated"…
x-mcp
Connect a user's own X (Twitter) dev app (BYOK) for the official X API MCP (reads) plus X v2 REST writes — post, reply, like, retweet, DM. Use when the user wants to act on X with their OWN X account or app — search, read timeline/users/news/trends/bookmarks via MCP, and post/reply/like/retweet/DM via REST. Walks…
social-x-post-card
Realistic X post card with engagement metrics (likes, reposts, views), suited to video overlays or shareable image cards.
social-x-post-card
A realistic X post card that displays a profile, handle, post text, optional quoted content or image area, and engagement figures such as likes, reposts, replies, and views. X is the social platform formerly known as Twitter.
x_guide
Essential guidance for using X (Twitter) tools correctly — search syntax, time filtering, and engagement patterns.
twitter-agent
Build and run a Twitter/X agent with a distinct personality and automated workflows.