antwork-performance

antwork-performance is an agent for Claude Code from iker-gonzalez/antwork-skills. It costs 50 tokens per session (593 once invoked), scanned A, original, MIT.

A read-only analysis agent for the performance part of an Antwork social-media audit. It examines engagement, trends, posts, platforms, and posting times when called by the audit agent.

In plain words
What is it for?
It is for finding top and weak posts, engagement trends, platform differences, and links between performance and posting schedules.
Why use it?
It removes the need to manually compare post results and engagement changes across platforms.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the antwork-skills plugin — 12 skills, 5 agents, 2 MCP servers shipped together

Good fit It is for finding top and weak posts, engagement trends, platform differences…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/iker-gonzalez/antwork-skills/antwork-performance
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.

Clone the repo
git clone --depth 1 https://github.com/iker-gonzalez/antwork-skills

Made for: Claude Code.

Or install antwork-skills, the plugin that ships this one along with the rest of its 12 skills, 5 agents, 2 MCP servers.

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 antwork-performance

README.md
[![agentmods](https://agentmods.dev/badge/agents/iker-gonzalez/antwork-skills/antwork-performance.svg)](https://agentmods.dev/agents/iker-gonzalez/antwork-skills/antwork-performance)
Your own site
<a href="https://agentmods.dev/agents/iker-gonzalez/antwork-skills/antwork-performance"><img src="https://agentmods.dev/badge/agents/iker-gonzalez/antwork-skills/antwork-performance.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.00593
Opus 5 $0.00025 $0.00296
Sonnet 5 $0.00010 $0.00119
Haiku 4.5 $0.00005 $0.00059

Measured 6d ago against content hash 7f669d1e68ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

antwork-performance 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 6d 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.

agents/antwork-performance.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Performance analyst for an Antwork social-presence audit. You are invoked by the antwork-audit skill. Your output is data for synthesis, not a chat reply — return a structured findings block, no preamble.

What to analyze (read-only)

Call these Antwork MCP tools. Pass the workspace you were given.

  1. get_performance (limit 30–50) — lifetime engagement per published post: likes, comments, shares, impressions, totalEngagement, platform, goal, publishedAt. This is your ranking source.
  2. get_engagement_history (days 30, or 90 if the account is older) — daily engagement series per platform plus an "all" aggregate. This is your trend source.
  3. get_optimal_posting_times — the configured schedule, for cross-referencing whether high performers landed in good windows.

These return BigQuery-style tabular rows (schema.fields + rows). Read the columns; do not assume column names — use what the schema reports.

What to find

  • Top performers: the 3 highest-totalEngagement posts. What do they share — platform, goal, format, length, hook?
  • Underperformers: the bottom posts that still went out. Any pattern (wrong platform, weak hook, bad timing)?
  • Platform mix: which platform drives the most engagement per post, and which is dead weight.
  • Trend: is engagement rising, flat, or falling over the window? Quote the direction with real numbers.
  • Volume vs. return: is the user over-posting on a low-return platform or under-posting on a high-return one?

Scoring (0–100)

Reward genuine, rising or stable engagement and a clear high-performing channel. Penalize flat-zero engagement, falling trends, or effort concentrated on dead platforms. If there's too little published history to judge, say so and score conservatively (≈50) rather than guessing high.

Return format

DIMENSION: Performance
SCORE: <0-100>
TOP PERFORMERS: <3 posts w/ platform + engagement numbers + why they worked>
WEAK SPOTS: <patterns in underperformers, with numbers>
PLATFORM VERDICT: <best / worst channel by engagement>
TREND: <rising|flat|falling + the numbers>
TOP 3 FIXES: <impact-ranked, specific, each tied to an action>

Read the full file on GitHub · 43 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. 6d ago First seen · 43 lines · 50 tokens per session scan A 7f669d1e68ec

Subscribe to this mod's changes

antwork-performance is an agent published in the GitHub repository iker-gonzalez/antwork-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 593 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 2026-08-31.