codebase-auditor

codebase-auditor is a skill for Claude Code from Jamie-BitFlight/claude_skills. It costs 85 tokens per session (1,920 once invoked), scanned A, original, MIT.

A repository-reading tool that examines source files to find how code behaves, which conventions it follows, and where new workflow steps could fit.

In plain words
What is it for?
Use it to inspect functions, map available data, identify coding patterns, and find suitable places to add or change agent workflows.
Why use it?
It answers questions from the actual code instead of relying on guesses or outdated documentation. It also shows what information the repository can provide to an agent.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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

Good fit Use it to inspect functions, map available data, identify coding patterns, and find suitable places to add or change agent workflows.

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

Any agent
npx skills add Jamie-BitFlight/claude_skills --skill codebase-auditor
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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/codebase-auditor.svg)](https://agentmods.dev/skills/jamie-bitflight/claude_skills/codebase-auditor)
Your own site
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/codebase-auditor"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/codebase-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,920 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 $0.00085 $0.01920
Opus 5 $0.00043 $0.00960
Sonnet 5 $0.00017 $0.00384
Haiku 4.5 $0.00009 $0.00192

Measured 3d ago against content hash 347979978005, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

codebase-auditor 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.

plugins/development-harness/skills/codebase-auditor/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Auditor

One research angle in a multi-angle technical research system. Singular focus: local codebase analysis — reading actual source files to extract behavioral contracts, coding conventions, workflow insertion points, and data availability maps.

Runs independently. Returns all findings as content to the caller.

Input

Audit target received from orchestrator:

$ARGUMENTS

Plugin Context Check

Before running any sub-mode, check whether the target path is inside a plugin directory.

If the target path contains plugins/ as a path component — apply the zip-and-move test to every design decision in this audit:

If this plugin directory were zipped, moved to a new machine, and unzipped at an arbitrary path — would the change still work?

Read plugins/development-harness/docs/plugin-deployment-model.md for the full gotchas and constraints. Key points:

  • Plugin scripts cannot reach outside their bundle after installation — no .claude/utilities/, no sibling plugins, no repo root paths
  • Any sys.path.insert that navigates above the plugin directory breaks after installation
  • Shared utilities must live inside the plugin bundle or be declared as installable package dependencies
  • If the audit covers scripts spanning both .claude/ and plugins/, flag the cross-boundary constraint explicitly in findings

Record the result: plugin-context: YES | NO at the top of your findings output.

Tool Discovery

Before running any sub-mode, identify the best available tools for code exploration. Run these checks once and record the results — do not repeat them per sub-mode.

# Relationship graph (most powerful for traversal — check first)
test -f graphify-out/graph.json && echo "graphify-graph:available" || echo "graphify-graph:absent"
which graphify 2>/dev/null && echo "graphify-cli:available" || echo "graphify-cli:absent"

# Semantic search
which ccc 2>/dev/null && echo "ccc:available" || echo "ccc:absent"

# Faster text search
which rg 2>/dev/null && echo "rg:available" || echo "rg:absent"

# AST-aware search
which ast-grep 2>/dev/null && echo "ast-grep:available" || echo "ast-grep:absent"
which semgrep 2>/dev/null && echo "semgrep:available" || echo "semgrep:absent"

Read the full file on GitHub · 179 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. 3d ago First seen · 179 lines · 85 tokens per session scan A 347979978005

Subscribe to this mod's changes

codebase-auditor is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (65 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 1,920 once invoked, about $0.0004 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens