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/adaline/gateway/claude-mdgit clone --depth 1 https://github.com/adaline/gatewayWrote 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/adaline/gateway/claude-md)<a href="https://agentmods.dev/instructions/adaline/gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/adaline/gateway/claude-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 | $0.01196 | $0.01196 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
gateway CLAUDE.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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Adaline Gateway
Project Overview
Adaline Gateway is a production-grade unified SDK ("Super SDK") for calling 300+ LLMs through a single TypeScript interface. It is fully local (not a proxy), strongly typed, and isomorphic. It supports batching, retries, caching, callbacks, OpenTelemetry, and tool calling.
Repository: https://github.com/adaline/gateway
Tech Stack
- Language: TypeScript 5.6
- Runtime: Node.js >=18
- Package Manager: pnpm >=9 (strictly enforced — never use npm or yarn)
- Build: tsup (ESM + CJS dual output)
- Monorepo: Turborepo
- Testing: Vitest
- Linting: ESLint (extends
eslint-config-adaline) - Formatting: Prettier (140 char width, double quotes, ES5 trailing commas)
- Validation: Zod schemas for all runtime types
- Git Hooks: Husky (pre-commit runs lint + test)
- Releases: Changesets
Repository Structure
core/
gateway/ — Main @adaline/gateway package (orchestrator, plugins, handlers)
providers/ — 12 LLM provider implementations (openai, anthropic, google, etc.)
packages/
types/ — @adaline/types — shared Zod schemas (Config, Message, Tool, Content)
provider/ — @adaline/provider — base provider interface and abstract classes
tools/
tsconfig/ — @adaline/tsconfig — shared TypeScript config
eslint-config/ — eslint-config-adaline — shared ESLint config
gateway-experiments/ — experimental tools
Common Commands
pnpm install # Install all dependencies
pnpm run build # Build all packages (turbo)
pnpm run test # Run all tests (vitest)
pnpm run lint # Lint all packages
pnpm run format # Format with Prettier
pnpm run clean # Remove node_modules, dist, .turbo
pnpm run dev # Start dev mode (watch)
Per-package (run from package directory):
pnpm run test # vitest run
pnpm run test:watch # vitest watch
pnpm run build # tsup
pnpm run lint # eslint
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.
- 3d ago First seen · 132 lines · 1,196 tokens per session scan A 812f4c2e2eff
gateway CLAUDE.md is an instructions file published in the GitHub repository adaline/gateway (605 stars, last pushed 1mo ago), licensed MIT. It adds 1,196 tokens to every session, about $0.0060 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
synalinks AGENTS.md
Instructions for SynaLinks/synalinks, covering agents.md, project overview, development commands, install dependencies and run tests with coverage.
synalinks CLAUDE.md
Instructions for SynaLinks/synalinks, covering claude.md, project overview, development commands, install dependencies and run tests with coverage.
langroid CLAUDE.md
Claude Code instructions for langroid/langroid, covering claude.md, commands, development, testing and linting and type checking.
trulens AGENTS.md
AGENTS.md instructions for truera/trulens, covering agents.md, setup commands, code style, testing instructions and test markers.
openllmetry CLAUDE.md
Instructions for traceloop/openllmetry, covering openllmetry repository guide, repository structure, nx workspace commands, run tests across all packages and run linting across all packages.
openlit AGENTS.md
AGENTS.md instructions for openlit/openlit, covering openlit agent rules, ce/oss boundary, extension points, project hierarchy and ui and security.