codebase-research

A read-only codebase investigation that maps a project's structure, configuration, patterns, relevant code, and constraints before design work begins. It produces a grounded research summary without changing files.

In plain words
What is it for?
Use it to inspect a repository before designing a feature, locate related components and tests, understand its architecture, and record instructions or constraints for later work.
Why use it?
It prevents feature designs from being based on guesses about how an existing project works. It reveals reusable code, project conventions, dependencies, and technical limits early.

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/nickpolyder/np.copilot.config/codebase-research
Any agent
npx skills add NickPolyder/NP.CoPilot.Config --skill codebase-research
Clone the repo
git clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.Config

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 976 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 $0.00038 $0.00976
Opus 5 $0.00019 $0.00488
Sonnet 5 $0.00008 $0.00195
Haiku 4.5 $0.00004 $0.00098

Measured yesterday against content hash ca374eed056d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-research 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/codebase-research/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Intent (anchor): Produce a read-only, grounded research summary of an existing codebase before any design work starts. Always: discover structure first; identify existing patterns and relevant code; read project configuration; capture constraints and reusable abstractions. Never: edit files, design the feature, or generate implementation tasks.

Shared policy: Follow instructions/coordination.instructions.md for precedence, invocation, delegation, and handoffs. Apply instructions/workflow.instructions.md for proportional work and verification.

You are investigating what already exists so later design work is grounded in the actual project rather than assumptions.

Your goals are to:

  • Map the codebase — understand directory layout, key configuration, and entry points.
  • Identify patterns — capture frameworks, architecture style, naming conventions, and test approach.
  • Find relevant code — locate modules, services, components, or tests connected to the requested feature area.
  • Document constraints — note dependencies, tech debt, abstractions, and project-specific instructions that later phases must respect.

When to use this skill

Use this skill whenever:

  • A feature idea needs research before design decisions are made.
  • The user asks to investigate, explore, summarize, or understand a codebase area.
  • A later feature-design-doc should be grounded in real project structure, patterns, and constraints.
  • You need the first atomic step in the chain: codebase-researchfeature-design-doctask-breakdownimplementation-runner.

Do not use this skill for:

  • Design work — use feature-design-doc.
  • Task generation — use task-breakdown.
  • Implementation — use implementation-runner.
  • End-to-end gated planning and implementation — recommend prd-workflow instead of nesting it.

Workflow

Before designing anything, understand what exists.

  1. Discover project structure — read directory layout, key config files, entry points.
  2. Identify existing patterns — frameworks, architecture style, naming conventions, test approach.
  3. Find relevant code — modules, services, or components related to the feature area.
  4. Note constraints — dependencies, tech debt, existing abstractions that must be reused.
  5. Check project config — if .github/instructions/project-config.instructions.md exists, read it for framework, infra, and tooling choices.

Read the full file on GitHub · 105 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. yesterday First seen · 105 lines · 38 tokens per session scan A ca374eed056d

Subscribe to this mod's changes

codebase-research is a skill published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 7d ago), licensed MIT. It adds 38 tokens to every session and 976 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