Corpus Setup Guide

A setup guide for Corpus MCP Server, a server that builds a searchable collection of an organisation's GitHub repositories. It explains the required software, GitHub access token, environment settings, build commands, and Antigravity registration.

In plain words
What is it for?
Installing dependencies, fetching and building the corpus and system map, starting the server, and configuring it for Antigravity.
Why use it?
It gives new developers the steps and credentials needed to create their own local corpus when no shared one is available.

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/vampslayer/corpus/setup
Any agent
npx skills add VampSlayer/Corpus --skill setup
Clone the repo
git clone --depth 1 https://github.com/VampSlayer/Corpus

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 822 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00016 $0.00822
Opus 5 $0.00008 $0.00411
Sonnet 5 $0.00003 $0.00164
Haiku 4.5 $0.00002 $0.00082

Measured yesterday against content hash d641fc8a7381, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

Corpus Setup Guide scanned grade B 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Antigravity natively supports MCP. You can configure this server globally by adding it to `~/.gemini/config/mcp_config.json`:
.agents/skills/setup/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup Corpus MCP Server

Welcome! Because there is no committed corpus to fall back on, every developer builds their own corpus using their own GitHub PAT.

Prerequisites

  1. Node.js: Ensure you are running Node.js 18 or higher.

    node -v
    
  2. GitHub PAT: Create a Personal Access Token (classic) with repo and read:org scopes, or a fine-grained token with access to all organization repositories and metadata/content read access.

Configuration

Create a .env file in the root of the repository with the following variables:

GIT_ORG=your-github-org
GIT_PAT=your-github-personal-access-token
ENABLE_GAP_REPORTING=false
GITHUB_PROJECT=your-github-org/doc-gaps-repo # Required only if ENABLE_GAP_REPORTING is true

Setup and Build

  1. Install dependencies:

    npm ci
    
  2. Start the server (this will automatically fetch and build the corpus and system map):

    npm start
    

    Alternatively, you can manually run the build pipeline before starting:

    npm run build:corpus
    npm run build:map
    npm run build
    

Registering with Antigravity

Antigravity natively supports MCP. You can configure this server globally by adding it to ~/.gemini/config/mcp_config.json:

{
  "mcpServers": {
    "corpus": {
      "command": "node",
      "args": ["/absolute/path/to/code-context-mcp/dist/src/index.js"],
      "env": {
        "GIT_ORG": "your-github-org",
        "DOTENV_CONFIG_PATH": "/absolute/path/to/code-context-mcp/.env",
        "CORPUS_DIR": "/absolute/path/to/code-context-mcp/corpus"
      }
    }
  }
}

Registering with Claude

To use Corpus with Claude Desktop or Claude Code, add it to your configuration.

Claude Desktop

Edit your claude_desktop_config.json:

{
  "mcpServers": {
    "corpus": {
      "command": "node",
      "args": ["/absolute/path/to/code-context-mcp/dist/src/index.js"],
      "env": {
        "GIT_ORG": "your-github-org",
        "GIT_PAT": "your-github-pat",
        "CORPUS_DIR": "/absolute/path/to/code-context-mcp/corpus"
      }
    }
  }
}

Read the full file on GitHub · 109 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 · 109 lines · 16 tokens per session scan B d641fc8a7381

Subscribe to this mod's changes

Corpus Setup Guide is a skill published in the GitHub repository VampSlayer/Corpus (0 stars, last pushed 13d ago), licensed MIT. It adds 16 tokens to every session and 822 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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