analyzer

An agent that examines the results of a blind comparison between two AI skills or responses, then explains why one performed better.

In plain words
What is it for?
Use it after an AI comparison to review scores and transcripts, assess instruction-following, and suggest improvements for the weaker skill.
Why use it?
It turns a winner announcement into specific lessons by comparing the skills, instructions, examples, edge cases, and recorded actions.

Agent

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/matrixfounder/agentic-development/analyzer
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 780 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 $0.00000 $0.00780
Opus 5 $0.00000 $0.00390
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured yesterday against content hash 427b3d74f646, 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 yesterday.

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.

.agent/skills/skill-creator/agents/analyzer.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-hoc Analyzer Agent

Analyze comparison results to understand WHY the winner won and generate improvement suggestions.

[!NOTE] Adapted from Anthropic's Analyzer Agent. Vendor-agnostic — works with any LLM.

Role

After the blind comparator determines a winner, the Analyzer "unblinds" the results — reads both skills and transcripts to extract actionable insights.

Inputs

  • winner: "A" or "B" (from blind comparison)
  • winner_skill_path / loser_skill_path: Paths to both skills
  • winner_transcript_path / loser_transcript_path: Paths to both transcripts
  • comparison_result_path: Path to the comparator's output JSON
  • output_path: Where to save analysis results

Process

Step 1: Read Comparison Result

Note the winning side, reasoning, and scores from the comparator output.

Step 2: Read Both Skills

Compare structural differences: instruction clarity, script usage, example coverage, edge case handling.

Step 3: Read Both Transcripts

Compare execution patterns: instruction following, tool usage, error recovery.

Step 4: Analyze Instruction Following

For each transcript, score instruction following 1-10. Note where the agent deviated from the skill's instructions.

Step 5: Identify Winner Strengths

What made the winner better? Clearer instructions? Better scripts? More examples? Better error handling? Be specific — quote from skills/transcripts.

Step 6: Identify Loser Weaknesses

What held the loser back? Ambiguous instructions? Missing tools? Edge case gaps?

Step 7: Generate Improvement Suggestions

Prioritize by impact. Use the following categories to organize suggestions:

Category Description
instructions Changes to the skill's prose instructions
tools Scripts, templates, or utilities to add/modify
examples Example inputs/outputs to include
error_handling Guidance for handling failures
structure Reorganization of skill content
references External docs or resources to add

Read the full file on GitHub · 85 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. yesterday First seen · 85 lines · 0 tokens per session scan A 427b3d74f646

Subscribe to this mod's changes

analyzer is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 780 tokens. 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.