Running Claude Code at zero per-token cost: the Max-plan OAuth shim pattern

A developer built an OAuth shim that allows Claude Code and other agentic systems to use the Anthropic Messages API through a Claude Max subscription, eliminating per-token costs. The shim, hosted at oauth.nucleusos.dev, proxies requests by substituting a Max-plan OAuth bearer token for an API key, requiring only two environment variable changes. The project, part of Eidetic Works, aims to reduce operational costs for multi-agent workloads.

If you're running Claude Code or any agentic system that calls the Anthropic Messages API, you're probably paying per token. For light use, that's fine. For multi-agent systems with parallel workloads, it adds up fast. There's a different model: Claude Max subscription. Flat monthly cost, no per-token billing. The problem is that Max exposes a browser OAuth flow, not an API key. Your agent code expects ANTHROPIC API KEY . Max doesn't give you one. We built a shim that bridges the two. oauth.nucleusos.dev is an HTTP wrapper that exposes the Anthropic Messages API endpoint at /v1/messages . Internally, it routes each request through a Max-plan OAuth bearer token instead of an API key. The interface is 1:1 with the native Anthropic API. To use it, set two environment variables in your agent: ANTHROPIC BASE URL=https://oauth.nucleusos.dev ANTHROPIC API KEY=<your-shared-secret Your existing Claude Code installation, any Claude SDK wrapper, or raw HTTP client keeps working without code changes. The billing model changes; the interface doesn't. Each incoming request hits an HMAC-validated gate the ANTHROPIC API KEY value you set is treated as a shared secret, compared with hmac.compare digest — no timing oracle . Valid requests get the Bearer token substituted and are forwarded to api.anthropic.com . The response streams back unchanged. Security model: the shim trusts whoever holds the shared secret. This is for personal or team use — not for handing out to arbitrary clients. If you're running it on a VPS for your own agent fleet, that's the threat model it's designed for. GET /health → 200 {"status": "ok"} /v1/messages with a real Claude model → returned actual Anthropic response shape, usage: {"input tokens": 17, "output tokens": 6} The initial PR 578, 2026-06-16 covered Claude only. Subsequent PRs added: USER nobody — the initial container ran as root, caught in review. HTTP TIMEOUT S bumped to 600 — the default 300s timeout was clipping long agent runs. Opus calls on complex prompts run long; you need the headroom. gemini keys.txt env override — you can bake a key file into the image for air-gapped deployments.Current deployment: OCI A1 ARM 24GB, Mumbai . CPU is the binding constraint on this instance, not RAM. Claude Max subscription: $100/month Pro tier or $200/month Max tier with higher usage limits . Anthropic API comparison for equivalent workloads depends heavily on your token mix. For a team running Claude Code across multiple parallel sessions with shared context, API costs can exceed $200/month easily. The breakeven calculation is specific to your token volume. We're not publishing specific numbers because our workload 5 AI agents, agentic coding sessions, multi-file context may not generalize to yours. The pattern is worth knowing; the math is worth running against your own usage. This isn't a production multi-tenant API. It's a single-org shim. If you need rate-limiting, per-user billing, or audit logs, you need more infrastructure than this. It also doesn't give you higher rate limits than Max plan imposes. If you're hitting Max-plan throttles under heavy load, the shim won't help. The Dockerfile and compose file are in the repo. The README covers the non-root deployment, env vars, and the gemini keys.txt override. The shim is ~200 lines of Python FastAPI . Not a framework. Inspectable in an afternoon. We're building Eidetic Works on our own agentic substrate. Claude Code is the primary execution surface. Token costs are a real operational cost for us, not a theoretical one. The shim was born from a direct cost problem, not from wanting to build infrastructure. The telemetry endpoint we shipped in the same cohort eidetic.works/api/telemetry/metrics is what lets us measure whether it's working — we can now count daemon installs without relying on download counts or manual surveys. The Gemini routing is v1 — it works but hasn't been load-tested under the same conditions as the Claude path. The next substantive addition is probably a structured logging layer so we can see which models are taking which paths at what latency. Right now it's effective but opaque. If you build on this pattern, drop a comment below — interested in what you add. Read more on what we're building at eidetic.works