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/epistates/sparx/postnpx skills add Epistates/sparX --skill postgit clone --depth 1 https://github.com/Epistates/sparXWhat 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 | $0.00039 | $0.03225 |
| Opus 5 | $0.00019 | $0.01613 |
| Sonnet 5 | $0.00008 | $0.00645 |
| Haiku 4.5 | $0.00004 | $0.00323 |
Grade A, and why
post 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 3d 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post to X via Browser
Publish a post or thread directly to X using chrome browser automation.
Input
The user provides one of:
- Post content directly as the argument
- "last" to use the output from a previous
/composeor/threadinvocation in this session - A thread as numbered tweets or clearly separated tweets
- Media to attach — a file path (image, GIF, video), a screenshot taken this session, or a request to screenshot a URL first via
/media
If the content includes a link reply (a separate reply containing a URL), handle that as a follow-up reply after the main post.
Pre-Flight
Before doing anything:
- Parse the input to determine: single post vs thread vs post + link reply vs post + media
- Validate character counts (each tweet ≤ 280 characters)
- If any tweet exceeds 280 characters, stop and ask the user to revise — do NOT truncate
- If media is referenced, determine the media type and upload path (see Step 5)
Process
Step 1 — Get Browser Context
mcp__claude-in-chrome__tabs_context_mcp(createIfEmpty: true)
Check if there's an existing tab on x.com. If yes, use it. If not, create a new tab.
Step 2 — Navigate to X
mcp__claude-in-chrome__navigate(url: "https://x.com", tabId: <tab>)
Wait for the page to load. Take a screenshot to verify you're on X and logged in.
mcp__claude-in-chrome__computer(action: "screenshot", tabId: <tab>)
If not logged in: Stop and tell the user they need to log in manually. Do NOT attempt to handle authentication.
Step 3 — Open Compose
Navigate directly to the compose URL (most reliable):
mcp__claude-in-chrome__navigate(url: "https://x.com/compose/post", tabId: <tab>)
Wait for the compose dialog to fully load:
mcp__claude-in-chrome__computer(action: "wait", duration: 2, tabId: <tab>)
Step 4a — Single Post
- Find the text input area in the compose dialog:
mcp__claude-in-chrome__find(query: "tweet text input area", tabId: <tab>)
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.
- 3d ago First seen · 338 lines · 39 tokens per session scan A b30571ea8ec3
post is a skill published in the GitHub repository Epistates/sparX (3 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 3,225 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 2026-08-31.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…
opencli-adapter-author
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.