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 instructions/orchidfiles/ungate/agents-mdgit clone --depth 1 https://github.com/orchidfiles/ungateWrote 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/instructions/orchidfiles/ungate/agents-md)<a href="https://agentmods.dev/instructions/orchidfiles/ungate/agents-md"><img src="https://agentmods.dev/badge/instructions/orchidfiles/ungate/agents-md.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 | $0.03240 | $0.03240 |
| Opus 5 | $0.01620 | $0.01620 |
| Sonnet 5 | $0.00648 | $0.00648 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade A, and why
ungate 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 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.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ungate — architecture and project structure
Purpose
Ungate is a Cursor extension that lets you use Claude, ChatGPT, and MiniMax subscriptions instead of paying for API tokens. It consists of a VS Code extension, a local HTTP proxy (Fastify), a Svelte WebUI, and a shared types/constants library.
Monorepo (pnpm workspace)
ungate/
├── apps/
│ ├── api/ # Local proxy server (Fastify + TypeScript)
│ ├── extension/ # VS Code / Cursor extension
│ └── web/ # Web UI (dashboard) in Svelte
├── packages/
│ ├── shared/ # Shared types, schemas, constants, helpers
│ └── dev-kit/ # Linter, vitest configs
└── scripts/ # Utilities (build, tunnel, check-tunnels)
Data flow
Cursor → Cloudflare Tunnel → Ungate API → Provider API. Cursor cannot call localhost, so a public tunnel URL is required. Ungate listens on a custom OpenAI Base URL, transforms requests into the target provider format and back.
apps/api — proxy server
Fastify server, spawned by the extension as a child Node.js process.
Entry points:
/v1/chat/completions— OpenAI-compatible endpoint, accepts requests from Cursor/v1/messages— Anthropic-compatible endpoint (direct proxy)/v1/analytics— request statistics/v1/auth/*— OAuth routes (Claude, ChatGPT)/v1/models— model list/v1/settings— settings
Architecture:
src/server.ts— Fastify initialization, plugin registrationsrc/config.ts— static configuration (URLs, OAuth, beta parameters)src/plugins/auth.ts— preHandler for API-key authentication
Routing (src/routes/):
openai.ts— main router: determines provider by model (MiniMax → mapped → Claude). Branch order matters and must stay consistent.anthropic.ts— direct proxy to Anthropic API with OAuth tokenanalytics.ts,auth.ts,health.ts,models.ts,settings.ts
Provider selection (src/orchestration/openai/model-routing.ts):
- MiniMax: model name prefix or
model_mappingsentry pointing to MiniMax upstream - OpenAI-mapped:
model_mappingsentry pointing to OpenAI (ChatGPT Codex) - Claude (Anthropic): default fallback path
- Each model ID maps to one provider (configured per-row in
model_mappings), not a global setting.
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 · 172 lines · 3,240 tokens per session scan A 04b7d25864e0
ungate AGENTS.md is an instructions file published in the GitHub repository orchidfiles/ungate (155 stars, last pushed 8d ago), licensed MIT. It adds 3,240 tokens to every session, about $0.0162 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
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.