forensic-deepdive-codebase

forensic-deepdive-codebase is a plugin for Claude Code from Dhevenddra/forensic-deepdive. Its manifest loads nothing; the 5 skills it bundles cost 614 tokens per session together, scanned A, original, Apache-2.0.

A plugin containing a forensic brief of a software project and five focused skills for exploring, debugging, assessing change impact, refactoring, and onboarding. Its brief is made of documents describing the project’s files, dependencies, history, mental model, and operating rules.

In plain words
What is it for?
Use it to explain an unfamiliar repository, investigate bugs, predict the effects of changes, plan refactoring, or prepare a new team member to work in the codebase.
Why use it?
It gives coding agents shared project knowledge and separate workflows for common codebase tasks. This reduces the need to rediscover the project structure and conventions each time.

Plugin 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.

Claude Code
/plugin marketplace add Dhevenddra/forensic-deepdive
agentmods
npx agentmods add plugins/dhevenddra/forensic-deepdive/v0_8_0
Clone the repo
git clone --depth 1 https://github.com/Dhevenddra/forensic-deepdive

Made for: Claude Code.

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 forensic-deepdive-codebase

README.md
[![agentmods](https://agentmods.dev/badge/plugins/dhevenddra/forensic-deepdive/v0_8_0.svg)](https://agentmods.dev/plugins/dhevenddra/forensic-deepdive/v0_8_0)
Your own site
<a href="https://agentmods.dev/plugins/dhevenddra/forensic-deepdive/v0_8_0"><img src="https://agentmods.dev/badge/plugins/dhevenddra/forensic-deepdive/v0_8_0.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 5 skills cost 614 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

forensic-deepdive-codebase 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 3d 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.

tests/fixtures/prior_release/v0_8_0/.claude-plugin/plugin.json · 37 lines

What it actually says

{
  "name": "forensic-deepdive-codebase",
  "version": "0.2.0",
  "description": "Forensic codebase brief for surface_v0_8_0 \u2014 five markdown artifacts (MAP, HOTPATHS, ARCHAEOLOGY, MENTAL_MODEL, AGENT_BRIEF) plus five single-intent Claude skills covering exploring / debugging / impact-analysis / refactoring / onboarding workflows.",
  "author": {
    "name": "forensic-deepdive"
  },
  "keywords": [
    "codebase",
    "onboarding",
    "knowledge-graph",
    "code-review"
  ],
  "skills": [
    {
      "name": "codebase-exploring",
      "path": ".claude/skills/codebase-exploring/SKILL.md"
    },
    {
      "name": "codebase-debugging",
      "path": ".claude/skills/codebase-debugging/SKILL.md"
    },
    {
      "name": "codebase-impact-analysis",
      "path": ".claude/skills/codebase-impact-analysis/SKILL.md"
    },
    {
      "name": "codebase-refactoring",
      "path": ".claude/skills/codebase-refactoring/SKILL.md"
    },
    {
      "name": "codebase-onboarding",
      "path": ".claude/skills/codebase-onboarding/SKILL.md"
    }
  ]
}
Contents

What it installs

The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 614 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 3d ago First seen · 37 lines scan A 0ee8da812e5c

Subscribe to this mod's changes

forensic-deepdive-codebase is a plugin published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 18d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.