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.
npx agentmods add skills/kambleakash0/agent-skills/deep-codebase-auditnpx skills add kambleakash0/agent-skills --skill deep-codebase-auditgit clone --depth 1 https://github.com/kambleakash0/agent-skillsWrote 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.
[](https://agentmods.dev/skills/kambleakash0/agent-skills/deep-codebase-audit)<a href="https://agentmods.dev/skills/kambleakash0/agent-skills/deep-codebase-audit"><img src="https://agentmods.dev/badge/skills/kambleakash0/agent-skills/deep-codebase-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00067 | $0.01850 |
| Opus 5 | $0.00034 | $0.00925 |
| Sonnet 5 | $0.00013 | $0.00370 |
| Haiku 4.5 | $0.00007 | $0.00185 |
Grade A, and why
deep-codebase-audit 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 — vocabulary to use in every suggestion
- DEPTH-GUIDE.md — how to classify dependencies and test across seams
- 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.
- Module — anything with an interface and an implementation (function, class, package, slice).
- Interface — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
- Implementation — the code inside.
- Depth — leverage at the interface: a lot of behaviour behind a small interface. Deep = high leverage. Shallow = interface nearly as complex as the implementation.
- Seam — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
- Adapter — a concrete thing satisfying an interface at a seam.
- Leverage — what callers get from depth.
- Locality — what maintainers get from depth: change, bugs, knowledge concentrated in one place.
Key principles (see GLOSSARY.md for the full list):
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 129 lines · 67 tokens per session scan A 0a4c1f6f19dd
deep-codebase-audit is a skill published in the GitHub repository kambleakash0/agent-skills (7 stars, last pushed 18d ago), licensed MIT. It adds 67 tokens to every session and 1,850 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 2026-08-31.
Other skills, from other repositories
audit-config
Audits a Minecraft server's configuration tree for performance, security and footgun issues and reports a prioritised fix list. Use whenever the user asks to "audit my config", "check my server config", "review paper-global.yml", "why is my server set up wrong", "is this config safe", "lint my server", or points at a…
learn-plugin-docs
Fetches and condenses the documentation for ANY Minecraft plugin or mod on demand into a local markdown reference. Use this skill whenever the user asks "how do I configure X", "what does X do", "where are X's docs", "set up X", "what are X's permission nodes/commands/config keys", or names any plugin you do not…
server-doctor
Diagnoses and maintains a running Minecraft server from local files and pasted output, read-only. Use whenever the user shares or points at a crash report, latest.log, or an error and asks why the server crashed, won't start, keeps crashing, freezes, or stopped responding; wants a health check or scorecard for a…
new-server-bootstrap
Bootstraps a brand-new Minecraft server from scratch (Paper, optionally with a Velocity proxy). Use whenever the user says "set up a new server", "start a Minecraft server from scratch", "how do I make a server", "fresh install", "download Paper", "what Java do I need", "first time server setup", "create a network"…
proxy-network
Sets up and troubleshoots Minecraft proxy networks with Velocity (recommended), BungeeCord or Waterfall. Use whenever the user mentions a proxy, Velocity, BungeeCord, Waterfall, "the network", "lobby server", "hub", multiple servers, "connect servers", server switching, velocity.toml, forwarding.secret, modern…
skript-author
Writes, debugs and explains Skript scripts (.sk) for Minecraft servers. Use whenever the user mentions Skript, a .sk file, "sk reload", SkBee, skript-reflect, SkQuery, skript-yaml, SkRayFall, a custom command/event written in Skript, "my script doesn't work", Skript variables, "on right click", "every X seconds", or…