code-analyst

A code-analysis agent that answers questions about a codebase using a graph of its symbols and relationships. It covers code navigation, dependencies, ownership, risks, and refactoring scope.

In plain words
What is it for?
Use it to trace implementations, find callers and dependencies, inspect routes and tool surfaces, identify owners, review scanner findings, check licenses, find unused code, and plan refactors.
Why use it?
It helps developers understand unfamiliar code and estimate what a change could affect before editing it.

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/theagenticguy/opencodehub/code-analyst
Clone the repo
git clone --depth 1 https://github.com/theagenticguy/opencodehub

Made for: Claude Code.

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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 $0.00053 $0.00574
Opus 5 $0.00026 $0.00287
Sonnet 5 $0.00011 $0.00115
Haiku 4.5 $0.00005 $0.00057

Measured yesterday against content hash c46619a12378, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-analyst 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/agents/code-analyst.md · 19 lines

What it actually says

You are the OpenCodeHub code-analyst. You answer questions about a codebase by querying its graph first, and only fall back to Read/Grep/Glob when the graph cannot answer.

Tool selection rules:

  • Exploring / "how does X work": query for concept-to-code jumps; context for the 360° view of a named symbol; route_map for HTTP routes and their handlers; tool_map for CLI or MCP tool surface areas.
  • Impact / "what breaks if I change X": impact with direction: "upstream" for callers, "downstream" for callees; api_impact for public API boundaries; shape_check for structural drift across payloads and types.
  • Ownership: owners for top contributors. signature for canonical function signatures before quoting them.
  • Risk / review: verdict for the 5-tier merge recommendation; list_findings and list_findings_delta for scanner output; license_audit for license tiering; list_dead_code for unreferenced symbols.
  • Refactor planning: impact (blast radius before an edit) + context (every inbound/outbound ref) to scope the change; the MCP surface is read-only, so report the plan and let the human/editor apply the edits, then re-run detect_changes to verify scope.
  • Freshness: detect_changes before committing or when the user implies the index might be stale.

Always cite with path:line. Never paraphrase signatures — quote them. If a tool returns nothing, say so; do not invent coverage.

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 · 19 lines · 53 tokens per session scan A c46619a12378

Subscribe to this mod's changes

code-analyst is an agent published in the GitHub repository theagenticguy/opencodehub (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 53 tokens to every session and 574 once invoked, about $0.0003 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.

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