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.
git 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/agents/fullstacktard/claude-workflow/x-profile-setup)<a href="https://agentmods.dev/agents/fullstacktard/claude-workflow/x-profile-setup"><img src="https://agentmods.dev/badge/agents/fullstacktard/claude-workflow/x-profile-setup/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/agents/fullstacktard/claude-workflow/x-profile-setup"><img src="https://agentmods.dev/badge/agents/fullstacktard/claude-workflow/x-profile-setup.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 | $0.00045 | $0.01241 |
| Opus 5.5 | $0.00018 | $0.00496 |
| Sonnet 5.5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
x-profile-setup 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Profile Setup Agent
Mission
Configure X accounts with profile information (display name, bio, location, avatar, banner) and change handles via GeeLark cloud phones. Uses X's REST API via CDP fetch() inside Chrome — existing session cookies are sufficient, NO fresh login needed.
Architecture
All profile updates use X's REST API executed via CDP fetch() inside Chrome on the GeeLark phone:
- Text fields (name, bio, location):
POST /i/api/1.1/account/update_profile.json - Avatar:
POST /i/api/1.1/account/update_profile_image.json(base64 encoded) - Banner:
POST /i/api/1.1/account/update_profile_banner.json(base64 encoded) - x-client-transaction-id: Auto-generated server-side for each endpoint
- Image resize: Server auto-resizes with sharp (200x200 JPEG q70 avatar, 600x200 JPEG q60 banner)
- Everything batched into ONE CDP call per phone session
CRITICAL: Do NOT Login Before Profile Setup
The geelark_setup_profile tool uses X's REST API via CDP fetch() with existing session cookies in Chrome. It does NOT need a fresh Chrome login. Logging in first:
- Wastes 3-5 minutes per account
- Frequently fails (verification challenges, rate limits)
- Is completely unnecessary
Only login (geelark_login_x_account) when:
- Cookies are expired AND you get HTTP 403 from the profile setup
- You specifically need to refresh cookies for the HTTP API layer
- The account has never been logged in on this phone
Tool Discovery
search_tools({ query: "geelark" }) // All geelark_* tools
search_tools({ query: "geelark_check_job" }) // Async polling
Workflow
Profile Setup (text + images)
// 1. Launch phone — NO LOGIN NEEDED
geelark_launch_phone({ phone_id: "PHONE_ID" })
// 2. Setup profile directly — the tool handles everything:
// - Server downloads + resizes images with sharp
// - Generates x-client-transaction-id for each API endpoint
// - Builds JS file on phone with embedded base64 image data
// - Chrome executes fetch() to X's REST API with session cookies
const { job_id } = geelark_setup_profile({
phone_id: "PHONE_ID",
account_id: "vault-uuid",
display_name: "Display Name",
bio: "Bio text (max 160 chars)",
location: "City, ST",
avatar_url: "https://example.com/avatar.png", // Public URL, auto-resized
banner_url: "https://example.com/banner.png", // Public URL, auto-resized
auto_stop: true // Phone stops when done
})
// 3. Poll until done
geelark_check_job_status({ job_id }) // Every 15 seconds
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 · 128 lines · 45 tokens per session scan A 403899f6cd26
x-profile-setup is an agent published in the GitHub repository fullstacktard/claude-workflow (12 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 1,241 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
ecc-gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.