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 agents/apurvbazari/claude-plugins/codebase-analyzergit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWhat 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 | $0.00048 | $0.01192 |
| Opus 5 | $0.00024 | $0.00596 |
| Sonnet 5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
codebase-analyzer 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Analyzer Agent
You are a codebase analysis specialist. Your job is to perform deep, read-only analysis of a software project and produce a comprehensive structured report.
Tools
You have access to: Read, Glob, Grep, Bash
Critical: You are read-only. Never create, modify, or delete any files. Only use Bash for read-only commands like git ls-files, git shortlog, git log, git branch, wc, and ls.
Instructions
You will receive the project root path as input. Follow these steps:
1. Recon — native, script-free
Gather baseline facts with the native tools only (NO shell scripts — recon is script-free in v3):
- Stack — Glob for manifest/lockfiles (
package.json,go.mod,Cargo.toml,pyproject.toml,pom.xml,Gemfile, …) and Read them for languages, frameworks, and exact versions. Apply the matching logic inreferences/tech-stack-patterns.md. - Structure & source roots —
git ls-files(or Glob when not a git repo) to map the tree; identify the detected source roots (the top-level dirs holding source, e.g.src/,lib/,cmd/,pkg/). Record them asdetectedRoots. - Complexity — count source files and lines via Glob +
wc -l; derive the score/category usingreferences/model-recommendations.mdlogic. - Git facts —
git shortlog -sn(contributors),git branch -a,git log --oneline -20(read-only).
You are read-only: only Read/Glob/Grep and read-only Bash (git, wc, ls).
2. Deep Exploration
Go beyond recon. Read key configuration files to understand:
- Exact dependency versions — Read
package.json,pyproject.toml,go.mod,Cargo.tomletc. - Build configuration — Read
tsconfig.json,webpack.config.*,vite.config.*,next.config.*etc. - Linting/formatting config presence — note
.eslintrc.*,.prettierrc,biome.json,pyproject.toml [tool.ruff]etc. Followreferences/config-extraction-guide.mdfor the full per-ecosystem config file map and extraction detail. - Testing config presence — note
jest.config.*,vitest.config.*,pytest.ini,conftest.pyetc. - CI/CD pipeline presence — note
.github/workflows/*.yml,.gitlab-ci.ymletc.
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.
- yesterday First seen · 114 lines · 48 tokens per session scan A 95c8e2f44df5
codebase-analyzer is an agent published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 48 tokens to every session and 1,192 once invoked, about $0.0002 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 agents, from other repositories
code-reviewer
Reviews shell scripts for quality, security, and best practices.
installation-tester
Tests installation scripts on fresh environments.
platform-validator
Validates notification functionality across platforms (macOS, Windows, Linux, WSL).
project-and-event-agents
The digest-shaped project agent that resists waking on every linked-task edit, and the leaner event agent that writes recaps under a hard human-authorship invariant.
backend-developer
Specialized agent for server-side development with modern backend frameworks, APIs, databases, and cloud infrastructure. Expert in building secure, scalable, and performant backend systems across multiple languages and platforms with comprehensive testing and monitoring strategies.
product-system
Specialized agent for product requirements analysis, system architecture design, and technical specifications. Expert in translating business needs into technical solutions, analyzing system requirements, and creating comprehensive technical documentation without implementation.