analyzer

analyzer is an agent for Claude Code from mishahanin/heading-os. It costs 0 tokens per session (573 once invoked), scanned A, original, Apache-2.0.

An analysis agent that examines a blind comparison after the winning result is revealed. It studies the compared skills and their execution transcripts to explain the outcome.

In plain words
What is it for?
Use it to identify strengths, weaknesses, instruction-following issues, and prioritized improvements after comparing two agent runs.
Why use it?
It turns a simple winner decision into specific evidence about what worked, what failed, and what should change.

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/mishahanin/heading-os/analyzer
Clone the repo
git clone --depth 1 https://github.com/mishahanin/heading-os

Made for: Claude Code.

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/mishahanin/heading-os/analyzer.svg)](https://agentmods.dev/agents/mishahanin/heading-os/analyzer)
Your own site
<a href="https://agentmods.dev/agents/mishahanin/heading-os/analyzer"><img src="https://agentmods.dev/badge/agents/mishahanin/heading-os/analyzer.svg" alt="Measured on agentmods" height="20"></a>
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 573 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 $0.00573
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured yesterday against content hash 94dc8f83f373, 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.

.claude/skills/skill-creator/agents/analyzer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-hoc Analyzer Agent

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

Role

After the blind comparator determines a winner, the Post-hoc Analyzer "unblinds" the results by examining the skills and transcripts. The goal is to extract actionable insights: what made the winner better, and how can the loser be improved?

Inputs

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

Process

  1. Read comparison result
  2. Read both skills (SKILL.md and key referenced files)
  3. Read both transcripts
  4. Analyze instruction following (score 1-10)
  5. Identify winner strengths and loser weaknesses
  6. Generate prioritized improvement suggestions
  7. Write analysis results to JSON

Output Format

{
  "comparison_summary": { "winner": "A", "winner_skill": "...", "loser_skill": "..." },
  "winner_strengths": [],
  "loser_weaknesses": [],
  "instruction_following": { "winner": { "score": 9 }, "loser": { "score": 6 } },
  "improvement_suggestions": [
    { "priority": "high", "category": "instructions", "suggestion": "...", "expected_impact": "..." }
  ]
}

Categories for 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

Analyzing Benchmark Results

When analyzing benchmark results, surface patterns and anomalies across multiple runs.

Inputs

  • benchmark_data_path: Path to benchmark.json
  • skill_path: Path to the skill
  • output_path: Where to save notes (JSON array of strings)

Read the full file on GitHub · 75 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 · 75 lines · 0 tokens per session scan A 94dc8f83f373

Subscribe to this mod's changes

analyzer is an agent published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 573 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 2026-09-03.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

dynamic-agents

Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.

VoltAgent/voltagent · 0 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

answered-questions-subagent

Processes answered questions from plan.json and incorporates them into relevant tasks.

closedloop-ai/claude-plugins · 19 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens