using-codebase-analyzer

A workflow for analyzing an unfamiliar or complex codebase, including its build process, files, data flows, tools, and agent behavior. A codebase is the complete collection of source code and related project files.

In plain words
What is it for?
Use it to classify the system, trace how it is built and operates, inspect artifacts and data movement, examine tool interactions, and reconstruct its intended design.
Why use it?
It provides a structured way to understand inherited or complicated software before drawing conclusions about how it works.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/quangphu1912/codebase-analyzer/using-codebase-analyzer
Any agent
npx skills add quangphu1912/codebase-analyzer --skill using-codebase-analyzer
Clone the repo
git clone --depth 1 https://github.com/quangphu1912/codebase-analyzer

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.01474
Opus 5 $0.00015 $0.00737
Sonnet 5 $0.00006 $0.00295
Haiku 4.5 $0.00003 $0.00147

Measured yesterday against content hash c6dc83567fed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-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.

skills/using-codebase-analyzer/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

classify-analysis-target is ALWAYS required. After classification, express lane lets you skip directly to any Track B skill (but Track A context may be missing).

digraph analysis_flow {
    rankdir=TB;
    node [fontname="monospace"];

    "User starts analysis" [shape=doublecircle];
    "classify-analysis-target" [shape=box, style=bold, label="classify-analysis-target\n(ALWAYS FIRST)"];
    "Express lane?" [shape=diamond];
    "Track A: Recon skills" [shape=box];
    "Check trigger signals\n+ security signals" [shape=diamond];
    "HIGH priority" [shape=box, style=filled, fillcolor="#ffcccc"];
    "MEDIUM priority" [shape=box];
    "LOW priority" [shape=box];
    "Track B Phase 1:\nProvenance + Build Pipeline" [shape=box];
    "Track B Phase 2:\nArtifacts + Data Flows + Agent Loop" [shape=box];
    "Track B Phase 3:\nTool Graph + Gates + Simulate + Prompt" [shape=box];
    "Phase 4:\nreconstruct-system-intent" [shape=box, style=bold];

    "User starts analysis" -> "classify-analysis-target";
    "classify-analysis-target" -> "Express lane?";
    "Express lane?" -> "Track B Phase 1:\nProvenance + Build Pipeline" [label=" yes\n(skip Track A)"];
    "Express lane?" -> "Track A: Recon skills" [label=" no"];
    "Track A: Recon skills" -> "Check trigger signals\n+ security signals";
    "Check trigger signals\n+ security signals" -> "HIGH priority" [label=" pause,\noffer deep dive"];
    "Check trigger signals\n+ security signals" -> "MEDIUM priority" [label=" continue,\npresent after"];
    "Check trigger signals\n+ security signals" -> "LOW priority" [label=" note\nfor summary"];
    "HIGH priority" -> "Track B Phase 1:\nProvenance + Build Pipeline";
    "MEDIUM priority" -> "Track B Phase 1:\nProvenance + Build Pipeline";
    "LOW priority" -> "Track B Phase 1:\nProvenance + Build Pipeline";
    "Track B Phase 1:\nProvenance + Build Pipeline" -> "Track B Phase 2:\nArtifacts + Data Flows + Agent Loop";
    "Track B Phase 2:\nArtifacts + Data Flows + Agent Loop" -> "Track B Phase 3:\nTool Graph + Gates + Simulate + Prompt";
    "Track B Phase 3:\nTool Graph + Gates + Simulate + Prompt" -> "Phase 4:\nreconstruct-system-intent";
}

Track A skills: identifying-tech-stack, mapping-architecture, tracing-dependencies, detecting-dead-code, inventorying-api-surface, analyzing-code-quality

Track B phases: Phase 1 (trace-codebase-provenance, analyze-build-pipeline) → Phase 2 (classify-repo-artifacts, trace-data-flows, analyze-agent-loop) → Phase 3 (extract-tool-graph, map-feature-gates, simulate-behavior, analyze-prompt-influence) → Phase 4 (reconstruct-system-intent)

Special: test-hypothesis, detect-hidden-contracts

Orchestration Skills (Development Workflow)

Beyond analysis, this plugin provides development orchestration:

Trigger Skill What It Does
"build", "create", "implement", "add feature" brainstorming Design-first before implementation
"plan this", "write a plan" writing-plans Spec -> bite-sized tasks
"implement plan" subagent-driven-development Fresh subagent per task, review between
"execute plan" executing-plans Batch execution with checkpoints
"debug", "error", "not working" systematic-debugging Root cause investigation
"write tests", "test this" test-driven-development RED-GREEN-REFACTOR
"review code", "check my work" requesting-code-review Dispatch reviewer subagent
"merge", "finish branch" finishing-a-development-branch Merge/PR workflow
"parallel", "concurrent" dispatching-parallel-agents Concurrent subagents
"verify", "done" verification-before-completion Verify commands pass

Read the full file on GitHub · 110 lines

Files

What ships with it

1 file 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.

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. yesterday First seen · 110 lines · 31 tokens per session scan A c6dc83567fed

Subscribe to this mod's changes

using-codebase-analyzer is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,474 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.

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

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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens