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/eigenwise/eigenwise-toolshed/model-gatewaynpx skills add Eigenwise/eigenwise-toolshed --skill model-gatewaygit clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshedWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/eigenwise/eigenwise-toolshed/model-gateway)<a href="https://agentmods.dev/skills/eigenwise/eigenwise-toolshed/model-gateway"><img src="https://agentmods.dev/badge/skills/eigenwise/eigenwise-toolshed/model-gateway.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.03168 |
| Opus 5 | $0.00021 | $0.01584 |
| Sonnet 5 | $0.00008 | $0.00634 |
| Haiku 4.5 | $0.00004 | $0.00317 |
Grade B, and why
model-gateway scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`env --write-user` remains an opt-in shared fallback for people who deliberately want one gateway URL in `~/.claude/settings.json` across every project. Claude Code gives a current project's `settings.local.json` higher How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
model-gateway
Two local processes give Claude Code native access to the user's ChatGPT subscription models:
claude-code-proxy (does OpenAI OAuth and translates Anthropic Messages API to the Codex
backend) and a shim router this plugin owns. ANTHROPIC_BASE_URL points at the shim: requests
for claude-gpt-* models are un-prefixed and go to the proxy, everything else passes through
to api.anthropic.com with the user's normal claude.ai login. The shim's /v1/models advertises
Codex models with a claude- prefix because Claude Code's model discovery drops ids that don't
start with claude/anthropic. That prefix is shared with the real Anthropic ids, so the route
is decided by the backend family segment (claude-gpt-*, claude-grok-*), never by the prefix.
All commands: node "${CLAUDE_PLUGIN_ROOT}/bin/model-gateway.js" <command>
First-time setup
Project-local wiring is the standard setup. env --write-project writes the current project's .claude/settings.local.json, so the gateway stays configured for this project's sessions and executor worktrees without putting a machine-local endpoint in a committed file. setup uses the same project-local target.
env --write-user remains an opt-in shared fallback for people who deliberately want one gateway URL in ~/.claude/settings.json across every project. Claude Code gives a current project's settings.local.json higher precedence, so doctor marks the winner [effective], names both files, and says that project-local wiring wins when their gateway modes disagree.
The SessionStart hook injects a one-line nudge while the gateway is in any half-configured
state; act on it. The user sees that same line in the transcript, because a state only they can fix used to
reach the model alone. Anything routine stays out of it, and the hook always exits 0 so the line survives:
run ensure yourself when you need an exit code. setup is one-shot and idempotent: it downloads the claude-code-proxy binary
(sha256-verified) and starts everything. Re-running it later is also the upgrade path.
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.
- 4d ago First seen · 180 lines · 42 tokens per session scan B 133b0febe837
model-gateway is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (37 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 3,168 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…