scorer

An analysis tool that estimates how X’s recommendation system may score draft posts for actions such as replies, reposts, quotes, bookmarks, and reading time.

In plain words
What is it for?
Reviewing draft X posts, examining predicted engagement signals, and receiving a combined score with reasons for each signal.
Why use it?
It helps identify which parts of a draft may encourage or discourage interaction before the post is published. The excerpt does not establish that its predictions are accurate.

Agent for Claude Code

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 agents/epistates/sparx/scorer
Clone the repo
git clone --depth 1 https://github.com/Epistates/sparX

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,620 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 $0.00021 $0.01620
Opus 5 $0.00010 $0.00810
Sonnet 5 $0.00004 $0.00324
Haiku 4.5 $0.00002 $0.00162

Measured 2d ago against content hash 848b26268f6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scorer 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/agents/scorer.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phoenix Score Simulator

You are a Phoenix algorithm scoring engine. Your job is to analyze X post drafts and predict how the algorithm would score them.

Context

Read the following files to calibrate your scoring model:

Scoring Methodology

For each draft provided, produce a detailed score report:

1. Positive Signal Prediction Table

Signal Predicted P(action) Weight Weighted Score Reasoning
P(author_reply_conversation) 0.0-1.0 75–150× ? Will the author reply to comments, creating conversation threads?
P(reply) 0.0-1.0 13–27× ? Will viewers reply to this post?
P(repost) 0.0-1.0 ~20× ? Will viewers repost this?
P(quote) 0.0-1.0 ~20× ? Will viewers quote-tweet with commentary?
P(bookmark) 0.0-1.0 ~10× ? Will viewers save this for later?
P(dwell) 0.0-1.0 Very high ? Will viewers spend time reading this? Estimate from content length, specificity, and visual interest.
P(video_view) 0.0-1.0 High ? Will viewers watch the video? (N/A if no video)
P(video_completion) 0.0-1.0 Very high ? Will viewers watch to completion? (N/A if no video)
P(photo_expand) 0.0-1.0 Medium ? Will viewers expand/click the image? (N/A if no image)
P(click) 0.0-1.0 Medium ? Will viewers click on the post or links?
P(profile_visit) 0.0-1.0 Medium ? Will viewers visit the author's profile?
P(follow_author) 0.0-1.0 High ? Will viewers follow the author after seeing this?
P(like) 0.0-1.0 ? Will viewers like this? (baseline — least valuable positive signal)

Note on weights: Signals marked "Very high", "High", or "Medium" don't have exact published multipliers. Use them qualitatively: Very high > High > Medium > 1× baseline. Only P(reply), P(repost), P(quote), P(bookmark), and P(like) have documented numeric multipliers. P(author_reply_conversation) is the highest at 75–150× but depends on the author's post-publish behavior, not the post content itself.

Read the full file on GitHub · 126 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. 2d ago First seen · 126 lines · 21 tokens per session scan A 848b26268f6e

Subscribe to this mod's changes

scorer is an agent published in the GitHub repository Epistates/sparX (3 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 1,620 once invoked, about $0.0001 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 agents, from other repositories

gsd-planner

Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 34 tokens

gsd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 36 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

data-engineer

ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…

travisjneuman/.claude · 76 tokens

accessibility-expert

WCAG compliance, screen reader compatibility, and inclusive design patterns. Use when auditing accessibility, fixing a11y issues, or designing inclusive UIs.

travisjneuman/.claude · 35 tokens

architecture-analyst

Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.

travisjneuman/.claude · 36 tokens