project-analysis

A process for building a clear map of an unfamiliar or complicated software project. It examines the project's purpose, structure, main code paths, dependencies, and risks.

In plain words
What is it for?
Use it when onboarding to a repository, reverse-engineering its architecture, documenting it, auditing it, evaluating risks, or planning substantial changes.
Why use it?
It reduces the time spent guessing how a large, old, messy, or multi-package codebase works. It also makes conclusions and remaining uncertainties explicit.

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/bamzzo/project-analysis-skill/project-analysis
Any agent
npx skills add Bamzzo/project-analysis-skill --skill project-analysis
Clone the repo
git clone --depth 1 https://github.com/Bamzzo/project-analysis-skill

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 2,293 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 $0.02293
Opus 5 $0.00044 $0.01146
Sonnet 5 $0.00017 $0.00459
Haiku 4.5 $0.00009 $0.00229

Measured 3d ago against content hash beb69e71f971, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-analysis 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.

project-analysis/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Analysis

Use this skill to turn an unfamiliar or messy project into a clear, actionable map. The goal is not only to summarize files, but to explain how the project works, where its core paths are, what can break, how to verify it, and what to do next.

Operating Principles

  • Inspect before concluding. Distinguish code facts, documentation facts, runtime facts, inferences, and open questions.
  • Prefer the project's real structure over generic architecture claims.
  • Find the main path first: input -> dispatch -> core logic -> external dependency -> state/output.
  • Keep uncertainty visible. Say "inferred from" when not verified by execution.
  • Tie important conclusions to evidence: file paths, commands, test output, configs, or docs.
  • Produce action-oriented output: what to read, run, test, fix, or avoid next.
  • Do not expose secrets. If scanning configs, mention secret presence generically and avoid printing values.
  • Avoid exhaustive file-by-file summaries. Explain the system by role, flow, boundary, and risk.

Choose Depth

If the user does not specify depth, use standard.

For very large repositories, start with the surface map even when the requested depth is deep or audit.

Depth Inspect Execute Output emphasis Required evidence
quick top-level docs, manifests, scripts, major directories read-only discovery only what it is, likely stack, key files, obvious risks, next commands files/commands inspected and major unknowns
standard docs, manifests, configs, entrypoints, core modules, tests/CI safe read-only commands; run lightweight verification only when clearly appropriate architecture map, startup path, main flow, verification path, next actions file paths for main claims and commands actually run
deep standard scope plus 1-3 traced high-value flows and relevant tests/contracts targeted tests/build/typecheck or dry runs when safe flow traces, state/contracts, failure modes, missing coverage file/line evidence for traced paths and verification limits
audit broad risk surface: config, auth, state, side effects, CI/CD, dependencies, tests validation, dry-run, read-only, or explicitly safe commands only evidence ledger, risk register, readiness judgment, prioritized remediation evidence for every major risk or explicit "Open" label

Read the full file on GitHub · 177 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 · 177 lines · 87 tokens per session scan A beb69e71f971

Subscribe to this mod's changes

project-analysis is a skill published in the GitHub repository Bamzzo/project-analysis-skill (22 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 2,293 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 2026-08-30.

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