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/api7/aisix-archived/agents-mdgit clone --depth 1 https://github.com/api7/aisix-archivedWhat 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 | $0.03729 | $0.03729 |
| Opus 5 | $0.01865 | $0.01865 |
| Sonnet 5 | $0.00746 | $0.00746 |
| Haiku 4.5 | $0.00373 | $0.00373 |
Grade A, and why
aisix-archived 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 2d 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 — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
For AI coding assistants (OpenCode, Cursor, Copilot, etc.): This file is the primary context source for AI assistants working on this codebase. Use it to understand project structure, coding conventions, and build commands.
For human contributors: See CONTRIBUTING.md for the contribution guide.
Project Overview
Rust-based AI gateway proxy supporting OpenAI, Anthropic, Gemini, and DeepSeek APIs. Built with Axum for HTTP, Tokio for async runtime, and etcd for configuration storage.
Includes a React-based admin UI (in ui/) for managing models, API keys, and a playground for testing chat completions.
Build, Lint, and Test Commands
Build
cargo build # Debug build
cargo build --release # Release build
Run
RUST_LOG=info cargo run
UI Development
cd ui
pnpm install --frozen-lockfile # Install dependencies
pnpm dev # Start dev server
pnpm build # Build for production
pnpm lint # Run ESLint
pnpm format # Format with Prettier
pnpm typecheck # Type check without emit
pnpm preview # Preview production build
Lint
cargo clippy --all-targets --all-features --locked -- -D warnings
Clippy warnings are treated as errors. Fix all warnings before committing.
Test
cargo test # Run all tests
cargo test --verbose # Run tests with verbose output
cargo test --test api # Run specific test file (tests/api.rs)
cargo test test_crud # Run specific test by name
cargo test --test admin::models_api # Run tests in specific module
cargo test -- --nocapture # Show test output
E2E Test
pnpm -C tests install --frozen-lockfile # Install e2e dependencies
pnpm -C tests test # Run all e2e tests
Format
cargo fmt # Format all code
cargo fmt -- --check # Check formatting without changes
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.
- 2d ago First seen · 465 lines · 3,729 tokens per session scan A 472a8b566093
aisix-archived AGENTS.md is an instructions file published in the GitHub repository api7/aisix-archived (59 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,729 tokens to every session, about $0.0186 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
gateway CLAUDE.md
Instructions for Portkey-AI/gateway, covering claude.md, project overview, development commands, core development and testing.
spiceai copilot-instructions.md
Copilot instructions for spiceai/spiceai, covering spice.ai agent instructions, data correctness — absolute top priority, evidence — no claim without a reproduction, build, test, lint (expensive — read first) and git & prs.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
CPA-Manager-Plus AGENTS.md
AGENTS.md instructions for seakee/CPA-Manager-Plus, covering repository rules, operation, layout, commands and architecture.
stride-gpt AGENTS.md
Instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.