Navigating Codebases with CodeGraph

A pre-indexed map of a codebase that records symbols, relationships, call paths, dependencies, and project structure. A symbol is a named piece of code such as a function, class, or type.

In plain words
What is it for?
Use it to find symbols, inspect their source, trace callers and callees, explore a project, or assess the likely impact of an edit in an indexed repository.
Why use it?
It reduces the need to scan many files to understand unfamiliar code or predict the effect of a change. It can show where code is defined, used, called, and affected.

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/pleaseai/claude-code-plugins/codegraph
Any agent
npx skills add pleaseai/claude-code-plugins --skill codegraph
Clone the repo
git clone --depth 1 https://github.com/pleaseai/claude-code-plugins

Made for: Claude Code, Codex.

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 871 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 $0.00107 $0.00871
Opus 5 $0.00053 $0.00436
Sonnet 5 $0.00021 $0.00174
Haiku 4.5 $0.00011 $0.00087

Measured yesterday against content hash 18a3162143cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Navigating Codebases with CodeGraph 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.

plugins/codegraph/skills/codegraph/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeGraph - Local Code Intelligence

CodeGraph gives you a pre-indexed knowledge graph of the current project — symbol relationships, call graphs, and code structure — so you can answer questions instantly instead of consuming tokens scanning files with grep, glob, and Read.

When to Use

First check: CodeGraph applies only in repositories it has indexed — a .codegraph/ directory exists at the repo root. If there is no .codegraph/ directory, skip CodeGraph entirely; indexing is the user's decision (suggest codegraph init only if they want it).

In an indexed repo, reach for CodeGraph before grep/find or reading files when you need to understand or locate code:

  • Explore / answer most code questions in one call → codegraph_explore (returns the relevant symbols' verbatim source plus the call paths between them)
  • Inspect one symbol (source + callers) or read a whole file with line numbers → codegraph_node
  • Search for a symbol, type, or concept by name/intent → codegraph_search
  • Trace callers — who invokes this function/method? → codegraph_callers
  • Trace callees — what does this function call? → codegraph_callees
  • Assess impact / blast radius of changing a symbol → codegraph_impact
  • List indexed files in the project → codegraph_files
  • Check index health / freshnesscodegraph_status

How to Use

  1. For broad questions ("how does X work?", "where is auth handled?"), start with codegraph_explore — it answers most code questions in a single call.
  2. To navigate relationships from a known symbol, use codegraph_node, then codegraph_callers / codegraph_callees.
  3. Before refactoring or renaming, run codegraph_impact to find everything affected.
  4. If the MCP tools are listed but deferred, load them by name via tool search.
  5. Shell fallback (no MCP client needed): npx -y @colbymchenry/codegraph explore "<symbols or question>" and npx -y @colbymchenry/codegraph node <symbol-or-file> print the same output as the MCP tools — portable even without a global codegraph install (drop the npx -y @colbymchenry/ prefix if the CLI is on your PATH).
  6. If a tool response shows a ⚠️ staleness banner naming a file, Read that file directly for live content — it was edited within the sync debounce window.

Read the full file on GitHub · 56 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 · 56 lines · 107 tokens per session scan A 18a3162143cb

Subscribe to this mod's changes

Navigating Codebases with CodeGraph is a skill published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 7d ago), licensed MIT. It adds 107 tokens to every session and 871 once invoked, about $0.0005 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

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