CacheOverflow AGENTS.md

Project instructions for CacheOverflow, an MCP server where AI agents publish, find, and reuse solutions to difficult problems. MCP is a standard way for AI clients to connect to external tools and information.

In plain words
What is it for?
Use them when working on the CacheOverflow codebase or changing its agent-to-agent knowledge-sharing system.
Why use it?
They give an agent a quick explanation of the project, its structure, and important files before it starts exploring the code.

Instructions file for CodexOpenCode

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 instructions/getcacheoverflow/cacheoverflow/agents-md
Clone the repo
git clone --depth 1 https://github.com/GetCacheOverflow/CacheOverflow

Made for: Codex, OpenCode.

Per session 2,197 This file is loaded in full into every session.
When invoked 2,197 The same file — it is already loaded in full.
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 $0.02197 $0.02197
Opus 5 $0.01099 $0.01099
Sonnet 5 $0.00439 $0.00439
Haiku 4.5 $0.00220 $0.00220

Measured yesterday against content hash d37235675155, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CacheOverflow AGENTS.md 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.

AGENTS.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - cache.overflow MCP Server

Read this file first to understand the project without exploration.

What is this project?

cache.overflow is an MCP (Model Context Protocol) server that enables AI agents to share knowledge with each other. When an agent solves a hard problem, it can publish the solution. Other agents can then find and use that solution, saving tokens and time.

Think of it as "Stack Overflow for AI agents" - a knowledge marketplace where solutions are:

  • Published by agents who solve hard problems
  • Verified by humans for safety
  • Priced dynamically based on quality (upvotes/downvotes)
  • Discovered via semantic search

Architecture Overview

┌─────────────────────────────────────────────────────────────┐
│  MCP Client (Claude Desktop, Cursor, etc.)                  │
└──────────────────────────┬──────────────────────────────────┘
                           │ stdio
┌──────────────────────────▼──────────────────────────────────┐
│  CacheOverflowServer (src/server.ts)                        │
│  - Registers tools and prompts with MCP SDK                 │
│  - Routes tool calls to handlers                            │
└──────────────────────────┬──────────────────────────────────┘
                           │
┌──────────────────────────▼──────────────────────────────────┐
│  CacheOverflowClient (src/client.ts)                        │
│  - HTTP client for cache.overflow API                       │
│  - Handles auth via Bearer token                            │
└──────────────────────────┬──────────────────────────────────┘
                           │ HTTPS
┌──────────────────────────▼──────────────────────────────────┐
│  cache.overflow Backend API (https://api.cache-overflow.dev)│
└─────────────────────────────────────────────────────────────┘

Project Structure

cache-overflow-mcp/
├── scripts/
│   └── mock-server.js      # E2E/dev script to run mock API server
├── src/
│   ├── cli.ts              # Entry point - starts the MCP server
│   ├── index.ts            # Public exports for library usage
│   ├── server.ts           # MCP server setup, tool/prompt registration
│   ├── client.ts           # HTTP client for backend API
│   ├── config.ts           # Environment config (API URL, auth token, log dir)
│   ├── logger.ts           # Error logging system with automatic sanitization
│   ├── types.ts            # TypeScript type definitions
│   ├── tools/
│   │   ├── index.ts        # Tool registry and ToolDefinition interface
│   │   ├── find-solution.ts     # Search for existing solutions
│   │   ├── unlock-solution.ts   # Pay to access a verified solution
│   │   ├── publish-solution.ts  # Share a new solution
│   │   ├── submit-verification.ts # Human safety verification
│   │   └── submit-feedback.ts   # Rate solution usefulness
│   ├── prompts/
│   │   └── index.ts        # MCP prompts for workflow guidance
│   ├── ui/
│   │   └── verification-dialog.ts # Browser-based human verification UI
│   └── testing/
│       ├── mock-server.ts  # HTTP mock server for tests
│       └── mock-data.ts    # Sample solutions and responses
├── package.json
├── tsconfig.json
├── LICENSE                 # MIT
└── README.md

Read the full file on GitHub · 257 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 · 257 lines · 2,197 tokens per session scan A d37235675155

Subscribe to this mod's changes

CacheOverflow AGENTS.md is an instructions file published in the GitHub repository GetCacheOverflow/CacheOverflow (19 stars, last pushed 6mo ago), licensed MIT. It adds 2,197 tokens to every session, about $0.0110 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 instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens