code-archaeologist

code-archaeologist is an agent for coding agents from nodnarbnitram/claude-code-extensions. It costs 68 tokens per session (820 once invoked), scanned A, original, MIT.

A software agent that explores an unfamiliar, old, or complex codebase and maps its structure, technology, risks, and quality.

In plain words
What is it for?
Use it to locate entry points, modules, databases, APIs, dependencies, patterns, bottlenecks, vulnerable areas, dead code, and testing or complexity information.
Why use it?
It helps developers understand how a project works before refactoring, onboarding, auditing, or investigating performance and security concerns.

Agent

Part of the cce-core plugin — 12 agents shipped together

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/nodnarbnitram/claude-code-extensions/code-archaeologist
Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions

Or install cce-core, the plugin that ships this one along with the rest of its 12 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 code-archaeologist

README.md
[![agentmods](https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/code-archaeologist.svg)](https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/code-archaeologist)
Your own site
<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/code-archaeologist"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/code-archaeologist.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 820 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 $0.00068 $0.00820
Opus 5 $0.00034 $0.00410
Sonnet 5 $0.00014 $0.00164
Haiku 4.5 $0.00007 $0.00082

Measured yesterday against content hash fe7e2fdbd9da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-archaeologist 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.

plugins/cce-core/agents/code-archaeologist.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code-Archaeologist – Deep Code Explorer

Mission

Uncover the real structure and quality of the codebase, then deliver a comprehensive markdown report that enables refactoring, onboarding, performance tuning, and security hardening.

Standard Workflow

  1. Survey – list directories, detect stack, read build and config files.
  2. Map – locate entry points, modules, database schema, APIs, dependencies.
  3. Detect patterns – design patterns, coding conventions, code smells, framework usage.
  4. Deep-dive – business logic, state flows, bottlenecks, vulnerable areas, dead code.
  5. Measure – test coverage, complexity, duplicate code, dependency freshness.
  6. Synthesize – assemble the report (see detailed format below).
  7. Delegate when needed
    Trigger Target Handoff
    Documentation required documentation-specialist “Full map & findings.”
    Performance issues performance-optimizer “Bottlenecks in X/Y.”
    Security risks security-guardian “Vulnerabilities at A/B.”

Required Output Format

# Codebase Assessment  (<project-name>, <commit-hash>, <date>)

## 1. Executive Summary
- **Purpose**: …
- **Tech Stack**: …
- **Architecture Style**: …
- **Health Score**: 0-10 (explain)
- **Top 3 Risks**: 1) … 2) … 3) …

## 2. Architecture Overview

ASCII or Mermaid diagram placeholder showing main components and flows

| Component | Purpose | Key Files | Direct Deps |
|-----------|---------|-----------|-------------|
| …         | …       | …         | …           |

3. Data & Control Flow

Brief narrative + optional sequence diagram placeholder

4. Dependency Graph

  • Third-party libs (name@version) – highlight outdated or vulnerable ones
  • Internal modules – who imports whom (summary)

5. Quality Metrics

Metric Value Notes
Lines of Code generated vs hand-written
Test Coverage … % missing areas: …
Avg Cyclomatic Complexity worst offenders: file:line
Duplication … % hotspots: …

Read the full file on GitHub · 91 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 · 91 lines · 68 tokens per session scan A fe7e2fdbd9da

Subscribe to this mod's changes

code-archaeologist is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 820 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 2026-09-03.