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 fullstacktard/claude-workflow --skill geelark-handle-changegit clone --depth 1 https://github.com/fullstacktard/claude-workflowWrote 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/fullstacktard/claude-workflow/geelark-handle-change)<a href="https://agentmods.dev/skills/fullstacktard/claude-workflow/geelark-handle-change"><img src="https://agentmods.dev/badge/skills/fullstacktard/claude-workflow/geelark-handle-change/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/fullstacktard/claude-workflow/geelark-handle-change"><img src="https://agentmods.dev/badge/skills/fullstacktard/claude-workflow/geelark-handle-change.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 | $0.00046 | $0.00697 |
| Opus 5.5 | $0.00018 | $0.00279 |
| Sonnet 5.5 | $0.00009 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
geelark-handle-change 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GeeLark Handle Change Skill
Change X/Twitter account handles (usernames) using GeeLark cloud phone automation. The tool navigates to X's settings page on a cloud phone, types the new handle, waits for X's real-time validation, and taps Save.
When to Use This Skill
- Changing an X account's handle/username
- Checking if a handle is available (attempt the change; X validates in real-time)
- Updating handles for managed accounts after domain/brand decisions
- Rotating handles on warming accounts
Tool Discovery
search_tools({ query: "geelark_change_handle" })
search_tools({ query: "geelark_check_job" })
Available Tools
| Tool | Purpose |
|---|---|
geelark_change_handle |
Start an async handle change job |
geelark_check_job_status |
Poll job progress/result |
Usage
Change a Handle
// 1. Start the handle change (async job)
geelark_change_handle({
phone_id: "phone-profile-id",
account_id: "vault-account-uuid",
new_handle: "mynewhandle",
auto_stop: true // optional, default true — stops phone after completion
})
// Returns: { job_id: "uuid", status: "running" }
// 2. Poll for completion (every 10-15 seconds)
geelark_check_job_status({ job_id: "uuid" })
// Returns: { status: "completed", result: { success: true, previousHandle: "oldname", newHandle: "mynewhandle" } }
Handle Taken
If the handle is already taken, X's real-time validation catches it before Save is tapped:
{
"status": "completed",
"result": {
"success": false,
"previousHandle": "oldname",
"newHandle": "takenhandle",
"error": "That username has been taken. Please choose another.",
"errorCode": "handle_taken"
}
}
Error Codes
| Code | Meaning |
|---|---|
handle_taken |
Another account already has this handle |
invalid_format |
Handle contains invalid characters or wrong length (must be 4-15, alphanumeric + underscore) |
rate_limited |
X is rate-limiting handle changes (try again later) |
save_failed |
Save button tap didn't succeed |
navigation_failed |
Could not load the settings page |
input_not_found |
Could not find the username input field |
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.
- 1mo ago First seen · 87 lines · 46 tokens per session scan A c238622cf741
geelark-handle-change is a skill published in the GitHub repository fullstacktard/claude-workflow (12 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 697 once invoked, about $0.0002 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 2026-09-01.
Other skills, from other repositories
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.