context-prime

A project-context checklist that reads a codebase's documentation, files, configuration, tests, and conventions before coding.

In plain words
What is it for?
Use it to understand a repository, identify its technologies and test setup, and load relevant context before making changes.
Why use it?
It reduces the chance of giving advice that conflicts with the project's structure, tools, or instructions.

Cursor rule

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 rules/roy2392/vibe-agents-rules/context-prime
Clone the repo
git clone --depth 1 https://github.com/roy2392/vibe-agents-rules
Per session 278 This file is loaded in full into every session.
When invoked 278 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00278 $0.00278
Opus 5 $0.00139 $0.00139
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured 3d ago against content hash 4fed1b48be73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-prime 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 3d 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.

Origin

This is a copy

100% identical to context-prime — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

project-rules/context-prime.mdc · 49 lines

What it actually says

Context Prime

Prime Claude with comprehensive project understanding.

Standard Context Loading:

  1. Read README.md for project overview
  2. Read CLAUDE.md for AI-specific instructions
  3. List project files excluding ignored paths
  4. Review key configuration files
  5. Understand project structure and conventions

Steps:

  1. Project Overview:

    • Read README.md
    • Identify project type and purpose
    • Note key technologies and dependencies
  2. AI Guidelines:

    • Read CLAUDE.md if present
    • Load project-specific AI instructions
    • Note coding standards and preferences
  3. Repository Structure:

    • Run: git ls-files | head -50 for initial structure
    • Identify main directories and their purposes
    • Note naming conventions
  4. Configuration Review:

    • Package manager files (package.json, Cargo.toml, etc.)
    • Build configuration
    • Environment setup
  5. Development Context:

    • Identify test framework
    • Note CI/CD configuration
    • Review contribution guidelines

Advanced Options:

  • Load specific subsystem context
  • Focus on particular technology stack
  • Include recent commit history
  • Load custom command definitions

Output:

Establish clear understanding of:

  • Project goals and constraints
  • Technical architecture
  • Development workflow
  • Collaboration parameters
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. 3d ago First seen · 49 lines · 278 tokens per session scan A 4fed1b48be73

Subscribe to this mod's changes

context-prime is a cursor rule published in the GitHub repository roy2392/vibe-agents-rules (11 stars, last pushed 1y ago), licensed MIT. It adds 278 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to context-prime, differing in 0 lines, and is treated as a copy.