deep-codebase-audit SKILL.md skillA

deep-codebase-audit from kambleakash0/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kambleakash0/agent-skills/deep-codebase-audit@v2.0.0

Pins v2.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kambleakash0/agent-skills
Path
skills/deep-codebase-audit/SKILL.md
Versions recorded
2
Latest version
v2.0.0, committed May 2, 2026
First version recorded
Mar 21, 2026
Size
8,265 bytes
Repository stars
10
License
MIT

Find deepening opportunities in a codebase, surfacing architectural friction and proposing refactors that turn shallow modules into deep ones. Use when the user wants to improve architecture, make a codebase more testable, consolidate tightly-coupled modules, or make it safer for AI agents to navigate and change.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Deep Codebase Audit

Surface architectural friction and propose **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability, AI-navigability, and leverage.

References for this skill are in the `references/` folder:

- [GLOSSARY.md](references/GLOSSARY.md) — vocabulary to use in every suggestion
- [DEPTH-GUIDE.md](references/DEPTH-GUIDE.md) — how to classify dependencies and test across seams
- [INTERFACES.md](references/INTERFACES.md) — how to explore alternative interfaces

## When to Use

Use this skill when:

- The user says the codebase feels messy, hard to change, or "not ready for AI".
- You want to improve testability and make future TDD or autonomous agent work more effective.
- You're about to invest heavily in AI-driven changes and want to reduce risk first.

Do **not** use this skill when the user just wants to ship a small feature — use `/incremental-tdd` instead.

## Glossary

Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in [GLOSSARY.md](references/GLOSSARY.md).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kambleakash0/agent-skills/deep-codebase-audit@sha256:0a4c1f6f19dd23f9

The line at the top of this page pins the label v2.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5vpldod7d23ftnzj.svg)](https://markdownregistry.com/a/art_5vpldod7d23ftnzj)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Mar 21, 2026 and May 2, 2026, about one every 42 days.

versioncommittedcommitsizeaudit
v2.0.0 latest2026-05-02 b5bb417 8,265 BA view · diff
v1.0.02026-03-21 65cbefb 5,649 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8265 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

kambleakash0/agent-skills · 10 stars · license MIT · pushed 2026-10-28 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5vpldod7d23ftnzj
GET https://markdownregistry.com/api/v1/resolve?ref=kambleakash0/agent-skills/deep-codebase-audit
GET https://markdownregistry.com/api/v1/blob/0a4c1f6f19dd23f99250f359c125b0f663bc30a29b392db108ec523a71642095

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from kambleakash0/agent-skills

code-review SKILL.md skill
kambleakash0/agent-skills · skills/code-review/SKILL.md · Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness…
v1.0.0 · audit A · 10 stars
context-pack SKILL.md skill
kambleakash0/agent-skills · skills/context-pack/SKILL.md · Compact the current conversation into a handoff document so a fresh agent can continue the work in the next session.
v1.0.1 · audit A · 10 stars
domain-glossary SKILL.md skill
kambleakash0/agent-skills · skills/domain-glossary/SKILL.md · Extract a DDD-style ubiquitous language glossary from the current conversation.
v1.0.0 · audit A · 10 stars
english-humanizer SKILL.md skill
kambleakash0/agent-skills · skills/english-humanizer/SKILL.md · Detects and removes AI-generated writing patterns from English text. Rewrites content to sound natural, authentic, and…
v1.2.1 · audit A · 10 stars
git-workflow SKILL.md skill
kambleakash0/agent-skills · skills/git-workflow/SKILL.md · Guided Git workflow assistant. Helps with branching strategies, writing conventional commits, opening pull requests…
v1.0.0 · audit A · 10 stars
grill-master SKILL.md skill
kambleakash0/agent-skills · skills/grill-master/SKILL.md · Relentlessly interview the user when they want to learn about a topic, plan, or design until you both reach a shared…
v1.0.0 · audit A · 10 stars
incremental-tdd SKILL.md skill
kambleakash0/agent-skills · skills/incremental-tdd/SKILL.md · Test-driven development with a strict red-green-refactor loop, vertical slices, and deep modules. Use to build features…
v1.0.0 · audit A · 10 stars
script-writer SKILL.md skill
kambleakash0/agent-skills · skills/script-writer/SKILL.md · Script-writer that drafts presentations, essays, emails, and slides using only the cognitive and persuasive heuristics…
v1.0.0 · audit A · 10 stars
slice-the-spec SKILL.md skill
kambleakash0/agent-skills · skills/slice-the-spec/SKILL.md · Turn a PRD into a Kanban-ready backlog of vertically sliced issues, with clear dependencies and HITL/AFK flags.
v1.0.0 · audit A · 10 stars
spec-to-plan SKILL.md skill
kambleakash0/agent-skills · skills/spec-to-plan/SKILL.md · Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices.
v1.0.0 · audit A · 10 stars
spec-writer SKILL.md skill
kambleakash0/agent-skills · skills/spec-writer/SKILL.md · Create a comprehensive Product Requirements Document from conversation and repo context. Use when the user wants a PRD…
v1.0.0 · audit A · 10 stars
teach-me SKILL.md skill
kambleakash0/agent-skills · skills/teach-me/SKILL.md · Teach the user a new skill or concept within this workspace. Stateful — the user's learning state persists across…
v1.0.0 · audit A · 10 stars

Every file in kambleakash0/agent-skills

Browse by kind, by grade A, or by owner.