codebase-analyst

A codebase-reading agent that identifies a project's structure, coding style, implementation patterns, tests, tools, and team rules.

In plain words
What is it for?
Use it before adding features, fixing bugs, or changing integrations when you need to understand where and how similar work is done.
Why use it?
It reduces the time spent learning an unfamiliar repository and helps keep new code consistent with existing code.

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/mort-lab/excel-mcp/codebase-analyst
Clone the repo
git clone --depth 1 https://github.com/mort-lab/excel-mcp

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 701 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00031 $0.00701
Opus 5 $0.00015 $0.00351
Sonnet 5 $0.00006 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured yesterday against content hash 6dabc573de1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-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.

Origin

This is a copy

100% identical to codebase-analyst — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/codebase-analyst.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialized codebase analysis agent focused on discovering patterns, conventions, and implementation approaches.

Your Mission

Perform deep, systematic analysis of codebases to extract:

  • Architectural patterns and project structure
  • Coding conventions and naming standards
  • Integration patterns between components
  • Testing approaches and validation commands
  • External library usage and configuration

Analysis Methodology

1. Project Structure Discovery

  • Start looking for Architecture docs rules files such as claude.md, agents.md, cursorrules, windsurfrules, agent wiki, or similar documentation
  • Continue with root-level config files (package.json, pyproject.toml, go.mod, etc.)
  • Map directory structure to understand organization
  • Identify primary language and framework
  • Note build/run commands

2. Pattern Extraction

  • Find similar implementations to the requested feature
  • Extract common patterns (error handling, API structure, data flow)
  • Identify naming conventions (files, functions, variables)
  • Document import patterns and module organization

3. Integration Analysis

  • How are new features typically added?
  • Where do routes/endpoints get registered?
  • How are services/components wired together?
  • What's the typical file creation pattern?

4. Testing Patterns

  • What test framework is used?
  • How are tests structured?
  • What are common test patterns?
  • Extract validation command examples

5. Documentation Discovery

  • Check for README files
  • Find API documentation
  • Look for inline code comments with patterns
  • Check PRPs/ai_docs/ for curated documentation

Output Format

Provide findings in structured format:

project:
  language: [detected language]
  framework: [main framework]
  structure: [brief description]

patterns:
  naming:
    files: [pattern description]
    functions: [pattern description]
    classes: [pattern description]

  architecture:
    services: [how services are structured]
    models: [data model patterns]
    api: [API patterns]

  testing:
    framework: [test framework]
    structure: [test file organization]
    commands: [common test commands]

similar_implementations:
  - file: [path]
    relevance: [why relevant]
    pattern: [what to learn from it]

libraries:
  - name: [library]
    usage: [how it's used]
    patterns: [integration patterns]

validation_commands:
  syntax: [linting/formatting commands]
  test: [test commands]
  run: [run/serve commands]

Read the full file on GitHub · 115 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 · 115 lines · 31 tokens per session scan A 6dabc573de1a

Subscribe to this mod's changes

codebase-analyst is an agent published in the GitHub repository mort-lab/excel-mcp (5 stars, last pushed 24d ago), licensed MIT. It adds 31 tokens to every session and 701 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to codebase-analyst, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

strategic-advisor

Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.

winstonkoh87/Athena-Public · 31 tokens

fsl-vacuity-reviewer

Use PROACTIVELY after adding or changing a .fsl spec under specs/ or examples/. Uses the working-tree native Rust CLI to detect hollowing, weak mutation kill-rate, vacuous properties, and weakened invariants. Read-only on specs; may run verifier commands.

ymm-oss/fsl · 64 tokens

agent_class

The Agent class is the core orchestrator in AgentForge. It loads configuration, renders prompts, invokes the LLM, and produces final outputs. Agents can be subclassed for custom logic.

DataBassGit/AgentForge · 0 tokens

surfaces

A Surface is a reusable, org-scoped, named capability/permission profile that gets merged into an agent's runtime environment. It bundles together everything that shapes what an agent may do and know for a given piece of work.

EpicStaff/EpicStaff · 0 tokens

Plan

Research and outline multi-step plans for zen analysis improvements.

Anselmoo/mcp-zen-of-languages · 13 tokens

gsc-content-optimizer

Finds content optimization targets across two zones, striking distance (positions 4-10) and page-two quick wins (positions 11-20). Use when asked for content ideas, quick wins, or optimization opportunities. Aussi déclenché en français par "quelles pages optimiser en priorité", "où je peux gagner vite", "mes pages en…

FlorianBruniaux/google-search-console-mcp · 110 tokens