code-context

A code-context manager creates and maintains a code-context.md file that summarizes a project's structure and behavior. The file can describe models, routes, components, data stores, architecture, and data flows.

In plain words
What is it for?
Use it to initialize or update the project's codebase summary, or remove that summary when it is no longer wanted. It can also perform a global uninstall.
Why use it?
It gives coding sessions a reusable summary of the codebase. This reduces the need to rediscover how the project is organized each time.

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

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,345 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00044 $0.03345
Opus 5 $0.00022 $0.01673
Sonnet 5 $0.00009 $0.00669
Haiku 4.5 $0.00004 $0.00334

Measured yesterday against content hash 52205582dc76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

code-context scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

allowed-tools: Agent Bash(ls *) Bash(git diff *) Bash(git log *) Bash(git rev-parse *) Bash(git ls-files *) Bash(git rm --cached *) Bash(rm -rf *) Glob Grep Read Write Edit
skills/code-context/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Context Manager

You manage the code-context.md file for this project. This file serves as a persistent codebase understanding cache — it eliminates the need for every Claude session to re-explore the codebase from scratch.

User instructions

$ARGUMENTS

Command routing

Parse the first word of the user's arguments to determine the command:


Init Command

Generate a comprehensive code-context.md from scratch. If a code-context.md already exists, read it first — preserve any sections that are still accurate and update/add sections that have changed or are missing. This allows re-initialization to build on prior work rather than starting from zero.

Step 1: Discover project structure

Start by understanding the project at a high level:

  1. Read the root package.json, Cargo.toml, go.mod, pyproject.toml, build.gradle, Package.swift, or equivalent to determine the tech stack
  2. Check for monorepo indicators: lerna.json, pnpm-workspace.yaml, workspaces in package.json, Cargo.toml workspace members
  3. Read any existing README.md, CLAUDE.md, ARCHITECTURE.md, or similar docs
  4. If code-context.md already exists, read it to understand what was previously documented
  5. Map the top-level directory structure

Step 2: Deep exploration

For each package/module in the project, explore thoroughly using the Agent tool with subagent_type: "Explore". Run multiple agents in parallel for independent packages.

For each package, capture:

Backend/API packages:

  • All database models/schemas with field names, types, indexes, relationships, and key methods
  • All API routes with HTTP method, path, auth requirements, and purpose
  • Middleware chain and what each middleware does
  • Service layer / business logic modules
  • Configuration and environment variables with defaults
  • Utility modules and what they export

Read the full file on GitHub · 283 lines

Files

What ships with it

1 file 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. yesterday First seen · 283 lines · 44 tokens per session scan C 52205582dc76

Subscribe to this mod's changes

code-context is a skill published in the GitHub repository leverj/claude-code-context (2 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 3,345 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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