review

review is a skill for Claude Code, Codex from Epistates/sparX. It costs 41 tokens per session (1,042 once invoked), scanned A, original, MIT.

A post-review skill for examining how published posts performed on X, the social platform formerly known as Twitter. It uses post links, engagement data, analytics screenshots, or a general request to review recent posts.

In plain words
What is it for?
Use it to review post performance, compare results with scoring predictions, identify what worked, and improve future posts.
Why use it?
It connects results such as views, replies, reposts, likes, bookmarks, and link clicks to lessons for future content.

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

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/epistates/sparx/review.svg)](https://agentmods.dev/skills/epistates/sparx/review)
Your own site
<a href="https://agentmods.dev/skills/epistates/sparx/review"><img src="https://agentmods.dev/badge/skills/epistates/sparx/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,042 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 $0.00041 $0.01042
Opus 5 $0.00020 $0.00521
Sonnet 5 $0.00008 $0.00208
Haiku 4.5 $0.00004 $0.00104

Measured 5d ago against content hash 4271456cac07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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 5d 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/review/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-Publish Performance Review

Analyze how published posts performed against Phoenix scoring predictions and extract actionable lessons for future content.

Input

The user provides one or more of:

  • Post URL(s) — to analyze directly
  • Engagement data — impressions, replies, reposts, likes, bookmarks, link clicks
  • Analytics screenshot — from X Premium analytics dashboard
  • General request — "review my recent posts" or "what's working?"

Process

Step 1 — Gather Performance Data

If the user provides a URL: Use WebFetch to read the post text and any publicly visible metrics. WebFetch can extract the post content, author, and basic engagement signals visible on the page.

For full authenticated metrics (detailed impression counts, bookmark counts, analytics dashboard data), suggest running /analyze [url] which uses chrome browser automation for logged-in access to richer data.

If the user provides raw data, use that directly.

Key metrics to capture:

  • Impressions — total eyeballs
  • Engagement rate — (all engagements / impressions) × 100
  • Reply count — most important engagement metric
  • Reposts — distribution amplifier
  • Bookmarks — quality signal
  • Likes — baseline (least important positive)
  • Profile visits — discovery signal
  • Follower change — growth impact
  • Video views / completion % (if applicable)
  • Link clicks (if applicable)

Step 2 — Score Against Phoenix Hierarchy

Map actual performance to algorithm signals:

Metric Value Algorithm Interpretation
Author reply threads ? 75–150× weight — did the author create conversation threads?
Replies ? 13–27× weight — [assessment]
Reposts ? ~20× weight — [assessment]
Bookmarks ? ~10× weight — [assessment]
Impressions vs followers ? Distribution multiplier — [assessment]
Likes ? 1× baseline — [assessment]
Engagement rate ? Overall quality signal — [assessment]

Read the full file on GitHub · 115 lines

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. 5d ago First seen · 115 lines · 41 tokens per session scan A 4271456cac07

Subscribe to this mod's changes

review is a skill published in the GitHub repository Epistates/sparX (3 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,042 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.