codebase-exploration

A codebase-navigation skill that first searches a code index to locate relevant symbols, files, and sections before reading code.

In plain words
What is it for?
Use it to explore a repository, find definitions and references, outline files, and retrieve relevant code sections.
Why use it?
It reduces broad, time-consuming code searches when answering questions about an unfamiliar project.

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/marcinhamiga/code-indexing-mcp/codebase-exploration
Any agent
npx skills add MarcinHamiga/code-indexing-mcp --skill codebase-exploration
Clone the repo
git clone --depth 1 https://github.com/MarcinHamiga/code-indexing-mcp

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 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 $0.00041 $0.00558
Opus 5 $0.00020 $0.00279
Sonnet 5 $0.00008 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured yesterday against content hash 72e30a4ae1ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-exploration 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.

src/code_indexing_mcp/skills/codebase-exploration/SKILL.md · 38 lines

What it actually says

You are exploring a codebase to answer: $question. If the question is missing or too vague to search against, ask the user with the AskUserQuestion tool before starting.

The core rule of this skill: narrow down with the index first; read files last. Do not fall back to Grep/Glob/Read for code exploration while the code-indexing-mcp tools are available.

1. Ensure the index is ready

  1. Call mcp__code-indexing-mcp__project_status for the target project. If the project is unknown, call mcp__code-indexing-mcp__list_projects and, if needed, mcp__code-indexing-mcp__init_project.
  2. If the index is missing or stale relative to the files in question, call mcp__code-indexing-mcp__index_project first. Tell the user if indexing will take a moment.

2. Narrow down semantically

  • mcp__code-indexing-mcp__search_code — issue several targeted natural-language queries derived from the question (the concept, the mechanism, the data it touches). Not one broad query.
  • mcp__code-indexing-mcp__find_symbol — once you have a concrete function/class/module name, jump straight to its definitions and references instead of more searching.

Keep a shortlist of candidate files and symbols; discard paths the results rule out.

3. Outline before reading

  • mcp__code-indexing-mcp__file_outline — get each candidate file's structure and decide which symbols matter. Never dump a whole file just to find one thing.

4. Read only what matters

  • mcp__code-indexing-mcp__get_chunk — pull the full body of the specific chunks that answer the question.
  • Use Read/Grep only for content the index does not cover (non-code files, unindexed paths, exact literal matches semantic search cannot express) — and say so when you do.

5. Answer

Answer the question with path:line references for every claim, the shortest explanation that is complete, and an explicit note of anything the index could not cover so the user knows what was not verified.

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 · 38 lines · 41 tokens per session scan A 72e30a4ae1ad

Subscribe to this mod's changes

codebase-exploration is a skill published in the GitHub repository MarcinHamiga/code-indexing-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 558 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