analyst Claude Code subagentA

analyst from smith-horn/skillsmith is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add smith-horn/skillsmith/.claude/agents/analysis/code-analyzer.md@git:20260722.ed981fe

Pins git:20260722.ed981fe in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
smith-horn/skillsmith
Path
.claude/agents/analysis/code-analyzer.md
Versions recorded
3
Latest version
git:20260722.ed981fe, committed Jul 22, 2026
First version recorded
Feb 14, 2026
Size
5,746 bytes
Repository stars
78
License
a license file GitHub does not identify

Advanced code quality analysis agent for comprehensive code reviews and improvements.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Code Analyzer Agent

An advanced code quality analysis specialist that performs comprehensive code reviews, identifies improvements, and ensures best practices are followed throughout the codebase.

## Core Responsibilities

### 1. Code Quality Assessment
- Analyze code structure and organization
- Evaluate naming conventions and consistency
- Check for proper error handling
- Assess code readability and maintainability
- Review documentation completeness

### 2. Performance Analysis
- Identify performance bottlenecks
- Detect inefficient algorithms
- Find memory leaks and resource issues
- Analyze time and space complexity
- Suggest optimization strategies

### 3. Security Review
- Scan for common vulnerabilities
- Check for input validation issues
- Identify potential injection points
- Review authentication/authorization
- Detect sensitive data exposure

### 4. Architecture Analysis
- Evaluate design patterns usage
- Check for architectural consistency
- Identify coupling and cohesion issues
- Review module dependencies
- Assess scalability considerations

### 5. Technical Debt Management
- Identify areas needing refactoring
- Track code duplication
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add smith-horn/skillsmith/.claude/agents/analysis/code-analyzer.md@sha256:0071fde76347d384

The line at the top of this page pins the label git:20260722.ed981fe, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7ghj63icgazpdz4s.svg)](https://markdownregistry.com/a/art_7ghj63icgazpdz4s)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in smith-horn/skillsmith/.claude/agents/analysis/code-analyzer.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of code-analyzer.md from somewhere else? Ask it: where did my code-analyzer.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 3 versions of this file, between Feb 14, 2026 and Jul 22, 2026, about one every 79 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260722.ed981fe latest2026-07-22 ed981fe 5,746 BA view · diff
git:20260506.2c6dec72026-05-06 2c6dec7 5,832 BA view · diff
git:20260214.8506a0e2026-02-14 8506a0e 5,734 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (5746 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

smith-horn/skillsmith · 78 stars · license a license file GitHub does not identify · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7ghj63icgazpdz4s
GET https://markdownregistry.com/api/v1/resolve?ref=smith-horn/skillsmith/.claude/agents/analysis/code-analyzer.md
GET https://markdownregistry.com/api/v1/blob/0071fde76347d384701d0a3be0469ee760034359cb30af822b80ba4d61addd58

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from smith-horn/skillsmith

code-analyzer Claude Code subagent
smith-horn/skillsmith · .claude/agents/analysis/code-review/analyze-code-quality.md · Advanced code quality analysis agent for comprehensive code reviews and improvements
v1.0.0 · audit A · 78 stars
system-architect Claude Code subagent
smith-horn/skillsmith · .claude/agents/architecture/system-design/arch-system-design.md · Expert agent for system architecture design, patterns, and high-level technical decisions
v1.0.0 · audit A · 78 stars
base-template-generator Claude Code subagent
smith-horn/skillsmith · .claude/agents/base-template-generator.md · Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new…
git:20260722.f9bf04f · audit A · 78 stars
byzantine-coordinator Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/byzantine-coordinator.md · Coordinates Byzantine fault-tolerant consensus protocols with malicious actor detection
git:20260214.8506a0e · audit A · 78 stars
crdt-synchronizer Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/crdt-synchronizer.md · Implements Conflict-free Replicated Data Types for eventually consistent state synchronization
git:20260214.8506a0e · audit A · 78 stars
gossip-coordinator Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/gossip-coordinator.md · Coordinates gossip-based consensus protocols for scalable eventually consistent systems
git:20260214.8506a0e · audit A · 78 stars
performance-benchmarker Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/performance-benchmarker.md · Implements comprehensive performance benchmarking for distributed consensus protocols
git:20260214.8506a0e · audit A · 78 stars
quorum-manager Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/quorum-manager.md · Implements dynamic quorum adjustment and intelligent membership management
git:20260214.8506a0e · audit A · 78 stars
raft-manager Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/raft-manager.md · Manages Raft consensus algorithm with leader election and log replication
git:20260214.8506a0e · audit A · 78 stars
security-manager Claude Code subagent
smith-horn/skillsmith · .claude/agents/consensus/security-manager.md · Implements comprehensive security mechanisms for distributed consensus protocols
git:20260214.8506a0e · audit A · 78 stars
coder Claude Code subagent
smith-horn/skillsmith · .claude/agents/core/coder.md · Implementation specialist for writing clean, efficient code
git:20260722.ed981fe · audit A · 78 stars
planner Claude Code subagent
smith-horn/skillsmith · .claude/agents/core/planner.md · Strategic planning and task orchestration agent
git:20260722.ed981fe · audit A · 78 stars

Every file in smith-horn/skillsmith

Other files named analyst

analyst SKILL.md skill
sipyourdrink-ltd/bernstein · templates/skills/analyst/SKILL.md · Evaluate proposals - feasibility, engineering payoff, risk.
git:20260521.ffa79b0 · audit A · 1,214 stars
analyst Cursor rule
csmar432/finai-research · .cursor/rules/analyst.mdc · 金融分析师核心能力与MCP工具使用规范
git:20260616.8eba436 · audit A · 110 stars
analyst SKILL.md skill
reply-team/jason-ai · skills/runtime/roles/analyst/SKILL.md · Use when Jason launches you as the analyst role on an ai_role work item — say what is working in this campaign from…
git:20261115.1a52521 · audit A · 9 stars
analyst SKILL.md skill
hollandkevint/data-product-operator · skills/analyst/SKILL.md · Build or update an evidence graph for a data analysis by linking the question, definitions, source versions, checks…
v0.1.0 · audit A · 5 stars

Browse by kind, by grade A, or by owner.