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/tiylabs/tiygate/agents-mdgit clone --depth 1 https://github.com/tiylabs/tiygateWrote 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/tiylabs/tiygate/agents-md)<a href="https://agentmods.dev/instructions/tiylabs/tiygate/agents-md"><img src="https://agentmods.dev/badge/instructions/tiylabs/tiygate/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 | $0.01187 | $0.01187 |
| Opus 5 | $0.00593 | $0.00593 |
| Sonnet 5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
tiygate 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Contributor guide for TiyGate, an open-source Rust AI Gateway. Preserve the crate layering described below; it is intentional and enforced.
Project Structure & Module Organization
This repository is a Cargo workspace with 8 crates and an embedded admin console:
crates/corecontains canonical IR, traits, and pipeline code. It must stay zero-I/O and free of concrete provider, protocol, or database dependencies.crates/protocolsimplements protocol codecs for chat completions, messages, responses, Gemini, and embeddings.crates/providersstores built-in provider metadata and auth;crates/provider-bedrockisolates heavy AWS Bedrock SDK dependencies.crates/store,crates/cache,crates/admin, andcrates/servercover config storage, embedding cache, Admin REST/OAuth, and thetiygatebinary.webui/is the React + TypeScript + Vite admin console, embedded withrust-embedand served at/admin/ui.docs/holds architecture and protocol capability docs;scripts/contains helper checks such asverify-deps.sh.- Tests live in
crates/<crate>/tests/for integration tests and inline#[cfg(test)]modules for unit tests.
Engineering Principles
Keep changes aligned with three project constraints:
- Reliability first: keep the request hot path resilient with fallback budgets, circuit breakers, ingress limits, graceful drain, and telemetry/logging off the hot path.
- Extensible by design: add providers, protocols, routing strategies, cache backends, and log sinks through existing trait/registration boundaries instead of central rewrites.
- Maintainable layering: keep
coreas canonical IR + traits only, use the IR to avoid N×N protocol coupling, document lossy protocol behavior indocs/protocol-capability-matrix.md, and isolate heavy dependencies in dedicated crates.
Build, Test, and Development Commands
Run commands from the repository root. Use make help for the full list.
make build # Build webui, then release Rust binary
make build-debug # Build webui, then debug Rust binary
make dev # Build webui and run tiygate-server with webui feature
make dev-server # Run Rust server only, without webui embedding
make dev-web # Start the WebUI Vite dev server
make check # cargo check --workspace --all-targets --all-features
make test # cargo test --workspace --all-features
make lint # rustfmt check, clippy -D warnings, and webui tsc
make fmt # Format Rust and WebUI code
make audit # Run cargo audit and npm audit
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 · 57 lines · 1,187 tokens per session scan A c6814217940f
tiygate AGENTS.md is an instructions file published in the GitHub repository tiylabs/tiygate (139 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,187 tokens to every session, about $0.0059 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
deltallm AGENTS.md
Instructions for deltawi/deltallm, covering repository instructions, required first step and precedence and maintenance.
inferrail CLAUDE.md
Claude Code instructions for domondi1/inferrail, covering inferrail — agent context, before major feature work, read, before implementing something substantial, ask, engineering rules and repo-level conventions.
ai-gateway AGENTS.md
AGENTS.md instructions for ferro-labs/ai-gateway, covering agents.md, project overview, current development snapshot, public-facing wording and build, test, and run commands.
1flowbase AGENTS.md
AGENTS.md instructions for taichuy/1flowbase, covering 记忆, 用户偏好, 本项目相关skill在, 本项目 skills and 质量控制.
sbproxy AGENTS.md
Instructions for soapbucket/sbproxy, covering sbproxy (rust workspace), pre-commit checks, changelog entries are fragments, not changelog.md edits, the gate validates the working tree; git push ships head and running the gate.
1flowbase CLAUDE.md
Claude Code instructions for taichuy/1flowbase, covering 记忆 and 用户偏好.