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.
npx agentmods add skills/projectcpu/project-cpu-mcp/operator-cpunpx skills add projectcpu/project-cpu-mcp --skill operator-cpugit clone --depth 1 https://github.com/projectcpu/project-cpu-mcpWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00030 | $0.01130 |
| Opus 5 | $0.00015 | $0.00565 |
| Sonnet 5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
operator-cpu 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project CPU
Load cpu_persona first. Authenticate for owner-scoped reads and actions. Use cpu_get_game_config as the live rulebook, then read only relevant state. Tool descriptions and results define current rules, prices, limits, and errors.
Use a decision loop: observe, compare, quote or preflight, act, verify. The Operator sets the objective, spend, and risk. Present relevant trade-offs without assuming an optimization target. Refresh state after a transaction or meaningful delay.
Game model
- Cells and ownership — the world is a finite sphere of Cell NFTs. A Cell can hold deposits, one building, a Warehouse, a Mode, a Process, and inbound Deliveries. This state follows the NFT; wallet ETH and $CPU do not.
- Reveal and resources — Reveal draws deposits and costs live ETH and $CPU. Raw-resource reservoirs are finite and closed: consumed raw material returns for later Reveals. Buildings and Recipes produce refined resources and wCPU.
- Buildings and Processes — a building must become Ready. Extractors mine deposits, crafters run Recipes, and an Active hub enables routing and resource trade. Mode selects output and may cost $CPU to change. A Process commits the Cell for bounded Batches and cannot be cancelled. Crafting takes inputs up front; mining draws from deposits as Cycles settle. Claim an ended Process to free its slot.
- Warehouse pressure — each resource has an Effective cap. Full means the Warehouse reached it. A Process Stalls when less than one Cycle of output fits. Responses include crafting, selling, withdrawing wCPU, or moving inventory.
- Logistics — Route endpoints are owned revealed Cells. Intermediate waypoints may be Virgin cells, owned Cells, or Active hubs. Other foreign revealed Cells are walls.
cpu_route_networkexports the endpoint components from the complete map;cpu_next_hopsgives a one-hop view of the same map. Transport submits one complete Route. A quote reserves nothing. Finalize an arrived Delivery before using its cargo. - Internal resource market — Active hubs host Lots of Warehouse resources priced in $CPU. Buying creates a Fill and Delivery; selling escrows resource units and may require Transport to the Hub. Hub Sale fees, Transit fees, and Syndicate economics apply.
- External Cell market — OpenSea orders trade whole Cell NFTs in the configured settlement currency. Actions bind to an exact
orderHash; marketplace and creator fees apply, and the Cell's game state follows its ownership. - Production objective — Recipe chains can produce wCPU at a CPU Forge.
cpu_withdrawconverts it into wallet $CPU while emission budget remains and may return a Partial tranche. The shared reserve is finite.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 45 lines · 30 tokens per session scan A 5ee85ee6e9da
operator-cpu is a skill published in the GitHub repository projectcpu/project-cpu-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,130 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…