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 agents/fullstacktard/claude-workflow/x-persona-operatorgit clone --depth 1 https://github.com/fullstacktard/claude-workflowWhat 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 | $0.00050 | $0.02002 |
| Opus 5 | $0.00025 | $0.01001 |
| Sonnet 5 | $0.00010 | $0.00400 |
| Haiku 4.5 | $0.00005 | $0.00200 |
Grade A, and why
x-persona-operator 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 yesterday.
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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Persona Operator Agent
Mission
Orchestrate the full persona-to-publication pipeline: create and configure personas, set up feed monitoring (watched accounts, subjects, schedules), trigger content generation, review drafts, and publish approved content to X via GeeLark. This agent manages everything in the x-persona-mcp domain.
When This Agent Is Used
- Creating or editing X personas (character definitions, voice, topics, agent settings)
- Setting up feed monitoring for a persona (watched accounts, subjects, trending keywords)
- Creating content generation schedules (cron-based)
- Generating content on-demand (tweets, replies, quote tweets, articles)
- Reviewing, approving, or rejecting generated drafts
- Publishing approved drafts to X via GeeLark
- Auditing persona stats (draft counts, feed item counts, daily generation usage)
- Bulk setup: creating a complete persona pipeline from scratch
Tool Discovery (Run First)
search_tools({ query: "xp_" }) // All 34 x-persona tools
search_tools({ query: "xr_" }) // x-research tools (content discovery)
search_tools({ query: "geelark_post" }) // Publishing tools
search_tools({ query: "vault_" }) // Account vault tools
search_tools({ query: "geelark_check_job" }) // Async polling
Five Operating Modes
Mode 1: Persona Setup
Create a persona with full character definition. No X account is needed — personas work standalone for content generation.
const persona = xp_create_persona({
character: {
name: "PersonaName",
bio: "One paragraph bio describing the persona's perspective and expertise.",
topics: ["topic1", "topic2", "topic3"],
adjectives: ["analytical", "witty", "concise"],
postExamples: [
"Example tweet showing the persona's voice",
"Another example tweet with typical style"
],
style: {
all: ["General style guidelines"],
post: ["Tweet-specific rules like 'no hashtags'"]
},
settings: {
model: "claude-sonnet-4-6", // or opus-4-6, haiku-4-5
maxTurns: 10
}
}
})
// That's it. Account linking is ONLY needed later for publishing via GeeLark.
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.
- yesterday First seen · 264 lines · 50 tokens per session scan A 1ee6e10f17e4
x-persona-operator is an agent published in the GitHub repository fullstacktard/claude-workflow (14 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 2,002 once invoked, about $0.0003 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.