analyzer

analyzer is an agent for coding agents from Vibe-Marketer/plugins-and-skills. It costs 273 tokens per session (1,819 once invoked), scanned A, original, MIT.

An analysis agent for reviewing the results of a blind comparison or benchmark after the identities of the options are revealed. It examines the instructions, outputs, and execution records to explain why one approach performed better.

In plain words
What is it for?
Use it after an A/B comparison, benchmark, or other evaluation to find recurring strengths and weaknesses. It helps suggest changes to the underlying instructions and workflows.
Why use it?
It turns evaluation results into concrete lessons instead of stopping at a winner and a score. It can expose unclear instructions, execution problems, and patterns linked to better results.

Agent

Part of the create-plugins plugin — 12 skills, 6 commands, 9 agents shipped together

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/vibe-marketer/plugins-and-skills/analyzer
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 agents.

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 analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/analyzer.svg)](https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/analyzer)
Your own site
<a href="https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/analyzer"><img src="https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 273 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,819 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 $0.00273 $0.01819
Opus 5 $0.00137 $0.00910
Sonnet 5 $0.00055 $0.00364
Haiku 4.5 $0.00027 $0.00182

Measured 3d ago against content hash 202891e3c4e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyzer 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 3d 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.

create-plugins/agents/analyzer.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<mode_1 name="post_hoc_analysis"> Triggered after a blind A/B comparison has been completed. Unblinds results and generates actionable improvement suggestions.

<step_2 name="read_skills"> Read both skill definitions (SKILL.md and supporting files) and the full outputs from each:

  • Understand what each skill was instructed to do
  • See how instructions translated to actual output
  • Identify gaps between instructions and execution </step_2>

<step_3 name="read_transcripts"> Read execution transcripts for both skills:

  • How did the skill interpret the task?
  • Where did execution diverge from instructions?
  • Were there tool failures or unexpected paths? </step_3>

<step_4 name="identify_patterns"> For the winner:

  • What instruction patterns led to superior output?
  • What structural decisions contributed to quality?
  • What domain knowledge was effectively leveraged?

For the loser:

  • Where did instructions fail to guide execution?
  • What was missing or unclear?
  • Where did the skill produce surface-level compliance instead of genuine fulfillment? </step_4>

<step_5 name="score_instruction_following"> Rate instruction-following quality for each skill on a 1-10 scale:

  • 1-3: Major deviations from instructions
  • 4-6: Partial compliance with notable gaps
  • 7-8: Good compliance with minor misses
  • 9-10: Excellent instruction following </step_5>

<step_6 name="generate_improvements"> Create prioritized improvement suggestions for the losing skill. Each suggestion includes:

  • Category: instructions, tools, examples, error_handling, structure, references
  • Priority: high, medium, low
  • Current: What exists now
  • Proposed: What should change
  • Expected impact: How this would improve output quality </step_6>

<output_format_posthoc>

Post-Hoc Analysis

Read the full file on GitHub · 227 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. 3d ago First seen · 227 lines · 273 tokens per session scan A 202891e3c4e6

Subscribe to this mod's changes

analyzer is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 273 tokens to every session and 1,819 once invoked, about $0.0014 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.