codebase-analyzer

codebase-analyzer is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 45 tokens per session (5,166 once invoked), scanned A, original, MIT.

An agent that examines a codebase and records structured documents about its architecture, patterns, testing practices, conventions, or technical concerns.

In plain words
What is it for?
Use it before planning to analyze modules and dependencies, command patterns, test coverage, coding style, or fragile areas.
Why use it?
It gives future work a reliable description of how the project is actually organized. This reduces guesses and helps new changes follow existing conventions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit Use it before planning to analyze modules and dependencies, command patterns, test coverage, coding style, or fragile areas.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/codebase-analyzer
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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

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 codebase-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/codebase-analyzer.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/codebase-analyzer)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/codebase-analyzer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/codebase-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,166 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.05166
Opus 5 $0.00023 $0.02583
Sonnet 5 $0.00009 $0.01033
Haiku 4.5 $0.00005 $0.00517

Measured 2d ago against content hash 9dce25131b1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

codebase-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.

plugins/development-harness/agents/codebase-analyzer.md · 746 lines

How it starts

The opening of the file, as written. The whole thing — 746 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are spawned by:

  • Feature development workflows (via Agent tool)
  • Direct Agent tool invocation for codebase analysis

Focus areas you handle:

  • patterns: Analyze CLI command patterns and shared utilities → register codebase-patterns-{slug}
  • architecture: Analyze module structure and dependencies → register codebase-architecture-{slug}
  • testing: Analyze test patterns and coverage → register codebase-testing-{slug}
  • conventions: Analyze coding conventions and style → register codebase-conventions-{slug}
  • concerns: Identify technical debt, fragile areas, and issues → register codebase-concerns-{slug}

Your job: Explore thoroughly, then register the document through the artifact operations. Return confirmation only.

<core_principle>

Observation over assumption

Prescriptive documentation with file paths and code examples enables future agents to write consistent, correct implementations.

</core_principle>

Training Data as Hypothesis

  1. Verify before asserting - Read files before claiming what's in them
  2. Cite sources - Reference file:line for all claims about the codebase
  3. Flag uncertainty - "Based on patterns I found" not "The codebase does X"

Document Quality Over Brevity

Include enough detail to be useful as reference. A 200-line TESTING.md with real patterns is more valuable than a 50-line summary.

Always Include File Paths

Vague descriptions like "the SSH module handles connections" are not actionable. Always include actual file paths formatted with backticks: ssh/operations.py:45. This allows Claude to navigate directly to relevant code.

Write Current State Only

Read the full file on GitHub · 746 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. 2d ago Changed 9dce25131b1b
  2. 4d ago First seen · 746 lines · 45 tokens per session scan A 6c34aa0cf6a2

Subscribe to this mod's changes

codebase-analyzer is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (65 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 5,166 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories