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/alrcatraz/astra-aigate/agents-mdgit clone --depth 1 https://github.com/alrcatraz/astra-aigateWrote 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/alrcatraz/astra-aigate/agents-md)<a href="https://agentmods.dev/instructions/alrcatraz/astra-aigate/agents-md"><img src="https://agentmods.dev/badge/instructions/alrcatraz/astra-aigate/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 | $0.04555 | $0.04555 |
| Opus 5 | $0.02278 | $0.02278 |
| Sonnet 5 | $0.00911 | $0.00911 |
| Haiku 4.5 | $0.00456 | $0.00456 |
Grade A, and why
astra-aigate 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
astra-aigate — AI Agent Project Context
Project Identity
- Name: astra-aigate
- Repository:
~/Projects/astra/astra-aigate/ - Identity: Independent project (NOT a GitHub fork), seeded from OmniRoute (MIT)
- License: MIT
What It Does
Unified AI service gateway web console managing three categories:
- LLM Providers — route /v1/chat/completions with combo fallback (290 in the catalog)
- MCP Servers — MCP gateway host: one server exposing multiple MCP endpoints, registered self-hosted MCPs (local stdio + remote HTTP/SSE)
- Auxiliary Services — health monitoring + reverse proxy for Camofox, SearXNG, etc.
UI ships 43 locales (British English base, zh-CN, zh-TW, and 40 more).
Tech Stack
| Layer | Choice |
|---|---|
| Runtime | Node.js 26 (container, trixie-slim) |
| Database | SQLite via better-sqlite3 (default) / PostgreSQL (opt-in) |
| API framework | Fastify (carried from OmniRoute) |
| MCP SDK | @modelcontextprotocol/sdk (TypeScript) |
| Frontend | Next.js 16 (App Router) + React 19 + Expo Design System |
| Auth | Password + API keys (JWT) |
| Deployment | Podman multi-stage standalone build |
| Frontend build | Next.js (webpack-only; Turbopack disabled) |
Source Code Origins
src/— OmniRoute's complete source (v3.8.50), fully preserved- LLM routing, provider/combo/API key management — from OmniRoute
- MCP gateway — Phase 3 (completed: registry + multi-endpoint + bridge + admin tools)
- Service monitoring — new, planned for Phase 4
- Expo Design System — Phase 1 (completed)
File Conventions
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 · 321 lines · 4,555 tokens per session scan A bd974d246554
astra-aigate AGENTS.md is an instructions file published in the GitHub repository alrcatraz/astra-aigate (1 stars, last pushed 4d ago), licensed MIT. It adds 4,555 tokens to every session, about $0.0228 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 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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.