project-cpu-mcp AGENTS.md

Project instructions for the Project CPU MCP server, a locally run connection to a blockchain game on the EVM network system.

In plain words
What is it for?
Use them when modifying, testing, or releasing the MCP server, especially when handling wallets, transactions, worktrees, or project structure.
Why use it?
They reduce mistakes when changing the server by defining wallet settings, network requirements, file organization, and mandatory worktree use.

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/projectcpu/project-cpu-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/projectcpu/project-cpu-mcp

Made for: Codex, OpenCode.

Per session 2,640 This file is loaded in full into every session.
When invoked 2,640 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 $0.02640 $0.02640
Opus 5 $0.01320 $0.01320
Sonnet 5 $0.00528 $0.00528
Haiku 4.5 $0.00264 $0.00264

Measured yesterday against content hash ba1fc87446af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-cpu-mcp 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 · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project CPU MCP Server

MCP server for a blockchain game on EVM (Abstract). Distributed via npm, runs locally via npx.

Two wallet modes via WALLET_MODE (defaults to paybox): paybox (browser OAuth and remote signing) or evm (private key in env, SIWE auth — requires PRIVATE_KEY). Session state persists to ~/.project-cpu/session.json.

The launch chain is Robinhood (chainId 4663). NETWORK is optional, defaults to robinhood, and rejects every other value at startup. Contract addresses are loaded from the game API GET /api/v1/config?network=robinhood. Set RPC_URL to override Robinhood's public RPC when sending transactions (e.g. reveal).

Worktrees

ALWAYS work in a worktree for ANY change — no exceptions. The moment a task will touch a file (code, config, workflow, docs, secrets — anything that gets committed), the FIRST action is to create a worktree. The main checkout stays on main as a read-only hub; never edit, branch, or commit in it. "It's a small/interactive/one-off change" is NOT an exception — every change goes through a worktree. Read-only work (exploring, answering questions, running tests/builds) may stay in the hub.

Branches: <type>/<kebab-slug>, type — conventional-commit (feat fix chore refactor test docs perf ci build revert); defaults to feat when no type is given.

  • YOU MUST create or re-enter worktrees with bash tools/harness/worktree-create.sh --name <type>/<slug> [--source PATH]. The command branches off the hub, copies local-only files, installs dependencies, and prints the absolute worktree path on stdout. Use that returned path as the working directory for every subsequent mutation. A name without a type becomes feat/<slug>. Never use git worktree add directly and never create a branch in the hub — both bypass the repository lifecycle.
  • Worktrees live in the sibling ../mcp-worktrees/<branch-slug> directory.
  • A new local-only (gitignored) file a worktree needs → add its path to HARNESS_LOCAL_FILES in tools/harness/worktree-common.sh so creation and safe cleanup use the same inventory.
  • Remove a worktree with bash tools/harness/worktree-cleanup.sh --target PATH [--source PATH]. Cleanup preserves local and unmerged work and keeps the branch by default. Installed dependencies and unchanged copies of the configured local files are reproducible lifecycle artifacts; changed local copies and all other ignored files remain protected. Use --discard-changes only after an explicit decision to destroy detected work, and use the independent --delete-branch flag only after an explicit decision to remove the branch. Never finish cleanup with hand-written recursive deletion.

Read the full file on GitHub · 173 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 · 173 lines · 2,640 tokens per session scan A ba1fc87446af

Subscribe to this mod's changes

project-cpu-mcp AGENTS.md is an instructions file published in the GitHub repository projectcpu/project-cpu-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 2,640 tokens to every session, about $0.0132 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 2026-08-31.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

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 · 7,104 tokens

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

vscode buildNext.instructions.md

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

langchain AGENTS.md

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

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

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