optimize

A guide for reviewing and rewriting draft posts for X using a scoring model based on the platform's Phoenix ranking system.

In plain words
What is it for?
Scoring a draft post or thread, reviewing a published X post, understanding reach problems, and producing an improved version.
Why use it?
It identifies weaknesses in a draft and suggests changes aimed at improving how widely the post may be shown.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/epistates/sparx/optimize
Any agent
npx skills add Epistates/sparX --skill optimize
Clone the repo
git clone --depth 1 https://github.com/Epistates/sparX

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.01518
Opus 5 $0.00018 $0.00759
Sonnet 5 $0.00007 $0.00304
Haiku 4.5 $0.00004 $0.00152

Measured 2d ago against content hash 83679a29ea9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize 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 2d 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.

.claude/skills/optimize/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize an X Post Draft

You are a Phoenix algorithm scoring engine. Analyze a draft post, identify weaknesses against the scoring model, and rewrite for maximum predicted reach.

Input

The user provides:

  • A draft post (or thread) they want optimized
  • An X post URL — read the actual published post via WebFetch, score it, and suggest an improved version
  • A URL to content they posted about — read it to understand context for better optimization

URL Resolution

If the input contains an X post URL (x.com or twitter.com), use WebFetch to read the post text. If you also need live engagement metrics to assess how it's currently performing, suggest the user run /analyze [url] which uses chrome for authenticated metric access.

For any other URL, read via WebFetch to understand the context behind the draft. See ../../../reference/url-reading.md.

Process

Step 1 — Load Scoring Context

Read these references:

Step 2 — Analyze the Draft

Score the draft against every Phoenix signal:

Positive Signal Analysis

Signal Score (0-10) Assessment
Dwell potential ? Will people spend time reading this?
Reply magnet ? Does this trigger genuine replies?
Bookmark worthy ? Would someone save this?
Repost/Quote appeal ? Would someone share this with their audience?
Follow trigger ? Does this make people want more from this author?
Hook strength ? Do the first 8-12 words stop the scroll?

Negative Signal Risk

Risk Score (0-10, lower is better) Assessment
"Not interested" risk ? Could this feel irrelevant to non-target viewers?
Engagement bait ? Does it use manipulative patterns?
Link penalty ? Are external links in the body?
Spam signals ? Excessive hashtags, salesy tone, etc.?

Read the full file on GitHub · 141 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2d ago First seen · 141 lines · 37 tokens per session scan A 83679a29ea9b

Subscribe to this mod's changes

optimize is a skill published in the GitHub repository Epistates/sparX (3 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,518 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.

Related

Other skills, from other repositories

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

remote-browser

Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.

browser-use/browser-use · 22 tokens

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…

jackwener/OpenCLI · 80 tokens

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…

jackwener/OpenCLI · 88 tokens

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…

browser-use/browser-use · 177 tokens

open-source

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…

browser-use/browser-use · 137 tokens