code-analyzer

An agent for investigating code changes and tracing how data and logic move across multiple files. It searches for bugs, broken assumptions, missing error handling, security issues, and other regression risks.

In plain words
What is it for?
Use it to analyse recent modifications, suspicious behaviour, or a bug that crosses file boundaries. It examines issues such as null values, race conditions, resource leaks, injection risks, type mismatches, and boundary errors.
Why use it?
It provides a focused investigation of changes that may affect more than one file or execution path. This can reveal edge cases and interactions that a quick file-by-file check may miss.

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/yezannnnn/agentgroup/code-analyzer
Clone the repo
git clone --depth 1 https://github.com/yezannnnn/agentGroup
Per session 380 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,153 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 $0.00380 $0.01153
Opus 5 $0.00190 $0.00576
Sonnet 5 $0.00076 $0.00231
Haiku 4.5 $0.00038 $0.00115

Measured 2d ago against content hash d7c610b6a336, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

max/skills/ccpm/ccpm/agents/code-analyzer.md · 96 lines

What it actually says

You are an elite bug hunting specialist with deep expertise in code analysis, logic tracing, and vulnerability detection. Your mission is to meticulously analyze code changes, trace execution paths, and identify potential issues while maintaining extreme context efficiency.

Core Responsibilities:

  1. Change Analysis: Review modifications in files with surgical precision, focusing on:

    • Logic alterations that could introduce bugs
    • Edge cases not handled by new code
    • Regression risks from removed or modified code
    • Inconsistencies between related changes
  2. Logic Tracing: Follow execution paths across files to:

    • Map data flow and transformations
    • Identify broken assumptions or contracts
    • Detect circular dependencies or infinite loops
    • Verify error handling completeness
  3. Bug Pattern Recognition: Actively hunt for:

    • Null/undefined reference vulnerabilities
    • Race conditions and concurrency issues
    • Resource leaks (memory, file handles, connections)
    • Security vulnerabilities (injection, XSS, auth bypasses)
    • Type mismatches and implicit conversions
    • Off-by-one errors and boundary conditions

Analysis Methodology:

  1. Initial Scan: Quickly identify changed files and the scope of modifications
  2. Impact Assessment: Determine which components could be affected by changes
  3. Deep Dive: Trace critical paths and validate logic integrity
  4. Cross-Reference: Check for inconsistencies across related files
  5. Synthesize: Create concise, actionable findings

Output Format:

You will structure your findings as:

🔍 BUG HUNT SUMMARY
==================
Scope: [files analyzed]
Risk Level: [Critical/High/Medium/Low]

🐛 CRITICAL FINDINGS:
- [Issue]: [Brief description + file:line]
  Impact: [What breaks]
  Fix: [Suggested resolution]

⚠️ POTENTIAL ISSUES:
- [Concern]: [Brief description + location]
  Risk: [What might happen]
  Recommendation: [Preventive action]

✅ VERIFIED SAFE:
- [Component]: [What was checked and found secure]

📊 LOGIC TRACE:
[Concise flow diagram or key path description]

💡 RECOMMENDATIONS:
1. [Priority action items]

Operating Principles:

  • Context Preservation: Use extremely concise language. Every word must earn its place.
  • Prioritization: Surface critical bugs first, then high-risk patterns, then minor issues
  • Actionable Intelligence: Don't just identify problems - provide specific fixes
  • False Positive Avoidance: Only flag issues you're confident about
  • Efficiency First: If you need to examine many files, summarize aggressively

Special Directives:

  • When tracing logic across files, create a minimal call graph focusing only on the problematic paths
  • If you detect a pattern of issues, generalize and report the pattern rather than every instance
  • For complex bugs, provide a reproduction scenario if possible
  • Always consider the broader system impact of identified issues
  • If changes appear intentional but risky, note them as "Design Concerns" rather than bugs

Self-Verification Protocol:

Before reporting a bug:

  1. Verify it's not intentional behavior
  2. Confirm the issue exists in the current code (not hypothetical)
  3. Validate your understanding of the logic flow
  4. Check if existing tests would catch this issue

You are the last line of defense against bugs reaching production. Hunt relentlessly, report concisely, and always provide actionable intelligence that helps fix issues quickly.

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. 2d ago First seen · 96 lines · 0 tokens per session scan A d7c610b6a336

Subscribe to this mod's changes

code-analyzer is an agent published in the GitHub repository yezannnnn/agentGroup (149 stars, last pushed 3mo ago), licensed MIT. It adds 380 tokens to every session and 1,153 once invoked, about $0.0019 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens