analyze-codebase

A read-only investigation of an existing software repository to explain how it works. It maps its architecture, dependencies, build and test health, important code paths, ownership boundaries, and technical risks.

In plain words
What is it for?
It is for code archaeology, migration planning, existing-product improvements, dependency reviews, architecture mapping, and identifying risky changes or test gaps.
Why use it?
It prevents changes from being proposed before the current system and its fragile areas are understood.

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/ashermahonin/agentic-skills/analyze-codebase
Any agent
npx skills add ashermahonin/agentic-skills --skill analyze-codebase
Clone the repo
git clone --depth 1 https://github.com/ashermahonin/agentic-skills

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 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 $0.00087 $0.00462
Opus 5 $0.00044 $0.00231
Sonnet 5 $0.00017 $0.00092
Haiku 4.5 $0.00009 $0.00046

Measured 3d ago against content hash 095d7c7b4a3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-codebase 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.

agentic/skills/analyze-codebase/SKILL.md · 55 lines

What it actually says

Analyze Codebase

Purpose

Slow the impulse to edit until the system has been understood. Produce an evidence-backed map of what exists, how it behaves, and where change would be risky.

Inputs

  • Read the repo orientation files and build/test commands.
  • List languages, frameworks, services, data stores, queues, and deployment pieces.
  • Find entrypoints, critical flows, and ownership boundaries.
  • Identify generated, vendored, or external code that should not be rewritten casually.

Decision process

  1. Map top-level directories to responsibilities.
  2. Trace the most important runtime flows from entrypoint to persistence or external boundary.
  3. Check build, test, lint, and local run instructions without changing source files.
  4. Identify hotspots: high-change files, large modules, unclear boundaries, test gaps, risky dependencies, and fragile contracts.
  5. Compare current architecture to the requested target and write migration risks before proposing edits.
  6. Stay read-only unless the user explicitly moves the work into implementation.

Decision boundaries

  • Use Context7 MCP for current library, framework, platform, API, CLI, and configuration documentation whenever the task depends on external technology behavior.

Decision record

  • Current-state scan
  • Codebase map
  • Hotspots and tech-debt list
  • Current architecture summary
  • Target gap notes
  • Migration plan inputs

Ready when

  • Back claims with file paths, commands, or observed behavior.
  • Do not infer architecture from folder names alone.
  • Separate actual current behavior from desired target behavior.
  • Call out unknowns instead of smoothing them over.

Handoff

Hand off evidence, high-risk files, safe write boundaries, and validation commands to architecture or decomposition.

References

  • references/scan-checklist.md: Use this checklist when scanning an existing repository.
Files

What ships with it

2 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.

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 · 55 lines · 87 tokens per session scan A 095d7c7b4a3c

Subscribe to this mod's changes

analyze-codebase is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 87 tokens to every session and 462 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 2026-08-31.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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