context-builder

context-builder is a skill for Claude Code, Codex from asgarovf/locusai. It costs 34 tokens per session (896 once invoked), scanned A, original, MIT.

A process for collecting project context before making implementation changes. It examines the codebase structure, dependencies, build tools, test setup, and existing coding patterns.

In plain words
What is it for?
Use it at the start of complex or multi-file work, before refactoring, or when joining a new project area. It helps identify frameworks, databases, validation tools, state management, package scripts, and testing conventions.
Why use it?
Starting with this information helps avoid breaking assumptions in an unfamiliar project. It also clarifies whether the project is a monorepo, meaning one repository containing multiple related packages, or a single package.

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/asgarovf/locusai/context-builder
Any agent
npx skills add asgarovf/locusai --skill context-builder
Clone the repo
git clone --depth 1 https://github.com/asgarovf/locusai

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for context-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/asgarovf/locusai/context-builder.svg)](https://agentmods.dev/skills/asgarovf/locusai/context-builder)
Your own site
<a href="https://agentmods.dev/skills/asgarovf/locusai/context-builder"><img src="https://agentmods.dev/badge/skills/asgarovf/locusai/context-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 896 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 $0.00034 $0.00896
Opus 5 $0.00017 $0.00448
Sonnet 5 $0.00007 $0.00179
Haiku 4.5 $0.00003 $0.00090

Measured 4d ago against content hash 7dc0ffb7e59f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-builder 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 4d 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.

skills/context-builder/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Builder

When to use this skill

  • Starting work on an unfamiliar codebase or module
  • Before implementing a feature that spans multiple files
  • When you need to understand existing patterns before writing code
  • Before refactoring to avoid breaking implicit contracts
  • When onboarding to a new project area

Step 1: Project Structure

Understand the high-level layout:

# Top-level structure
ls -la

# Directory tree (2 levels, excluding noise)
find . -maxdepth 2 -not -path '*/node_modules/*' -not -path '*/.git/*' -not -path '*/dist/*' | head -60

# Package manager and scripts
cat package.json | head -40

Key things to note:

  • Monorepo vs single package
  • Build system (webpack, vite, esbuild, tsc)
  • Test framework (jest, vitest, mocha)
  • Available scripts (lint, format, test, build)

Step 2: Dependencies

# Key dependencies
cat package.json | grep -A 30 '"dependencies"'

# Dev dependencies (reveals tooling choices)
cat package.json | grep -A 30 '"devDependencies"'

Identify:

  • Framework (React, Vue, Express, Fastify, etc.)
  • ORM/database (Prisma, TypeORM, Drizzle, etc.)
  • Validation (Zod, Joi, Yup, etc.)
  • State management (Redux, Zustand, etc.)
  • Testing tools (Jest, Vitest, Playwright, etc.)

Step 3: Configuration

Read configuration files to understand project conventions:

  • tsconfig.json — TypeScript settings, path aliases
  • .eslintrc / eslint.config.js — Linting rules
  • .prettierrc — Formatting rules
  • .env.example — Required environment variables
  • CLAUDE.md / LOCUS.md — AI agent instructions

Step 4: Patterns

Before writing new code, find existing patterns:

# How are API routes structured?
grep -r "router\.\|app\.\(get\|post\|put\|delete\)" --include="*.ts" -l

# How are components organized?
find src/components -name "*.tsx" -maxdepth 2

# How are tests structured?
find . -name "*.test.*" -o -name "*.spec.*" | head -20

# How are types/interfaces defined?
grep -r "^export interface\|^export type" --include="*.ts" -l | head -10

Read the full file on GitHub · 118 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. 4d ago First seen · 118 lines · 34 tokens per session scan A 7dc0ffb7e59f

Subscribe to this mod's changes

context-builder is a skill published in the GitHub repository asgarovf/locusai (23 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 896 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 2026-08-30.

Related

Other skills, from other repositories

repository-discovery

Use this skill to systematically explore an unfamiliar codebase before making any changes. Activates when starting work in an unknown repository, adding a new feature, debugging without prior context, or when no CONTEXT.md exists. Produces a grounded understanding of architecture, conventions, and constraints.

karthikrshet/aiskills · 61 tokens

explain-codebase

Drop into any repo and generate a structured architecture overview. Maps the codebase, identifies entry points, frameworks, and dependencies — then produces a "start here" guide for new contributors.

suryast/free-ai-agent-skills · 42 tokens

repo-onboarding

Systematically map an unfamiliar codebase before changing it — entry points, build/test loop, conventions, data flow. Use when starting work in a repo you haven't seen, or asked "how does this codebase work?".

jnMetaCode/skillet · 48 tokens

codebase-onboarding

Use when you land in an unfamiliar or inherited codebase and must get productive fast: a breadth-first map of entry points, request flow, module ownership, hidden side effects (cron, webhooks, workers) and churn hotspots, committed as CODEBASE-MAP.md. NOT a deep audit of one module (that is analyze) or chasing one…

ericrisco/rsc-harness · 83 tokens

project-map

Generates a compact structural orientation document (.agentic/project-map.md) so any agent can understand codebase structure without filesystem exploration. Invoked when onboarding to a codebase, exploring unfamiliar projects, or auditing code layout and conventions.

soulcodex/agentic · 49 tokens

codebase-analysis

Analyzes codebase to find similar features, reusable utilities, and architectural patterns.

mehdic/bazinga · 19 tokens