Borrowing it
Nothing to install: this file belongs to julianduque/heroku-ai-provider. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/julianduque/heroku-ai-provider/main/AGENTS.mdgit clone --depth 1 https://github.com/julianduque/heroku-ai-providerWrote 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/julianduque/heroku-ai-provider/agents-md)<a href="https://agentmods.dev/instructions/julianduque/heroku-ai-provider/agents-md"><img src="https://agentmods.dev/badge/instructions/julianduque/heroku-ai-provider/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/julianduque/heroku-ai-provider/agents-md"><img src="https://agentmods.dev/badge/instructions/julianduque/heroku-ai-provider/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00595 | $0.00595 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
heroku-ai-provider 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 9d 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Core provider code lives in src/, with src/models covering chat and embedding adapters and src/utils housing shared helpers. Jest suites reside in tests/, including tests/setup.ts for shared configuration. Example agents and integration playgrounds are under examples/, while generated TypeDoc content is stored in docs/. Build artifacts land in dist/; regenerate them via the build pipeline instead of editing them directly. Supporting scripts (such as CommonJS fixes) are in scripts/.
Build, Test, and Development Commands
Install dependencies with pnpm install. Use pnpm build to clean and emit both ESM and CJS bundles, and pnpm docs to refresh the API reference. Run pnpm test for the default Jest suite, pnpm test:watch during active development, and pnpm test:coverage before releases. pnpm lint checks the codebase with ESLint, while pnpm format applies Prettier. Try pnpm example:tool-loop to exercise the agent tool-call loop locally.
Coding Style & Naming Conventions
This project targets modern TypeScript and enforces 2-space indentation via Prettier and ESLint (eslint.config.mjs). Prefer named exports from modules and keep filenames lowercase with hyphens or descriptive nouns (e.g., chat.ts). Use camelCase for functions and variables, PascalCase for types and classes, and reserve UPPER_SNAKE_CASE for environment constants. Avoid ambient any; annotate public APIs explicitly so generated declarations stay accurate.
Testing Guidelines
All automated tests run through Jest with ts-jest. Place new specs alongside peers in tests/** using the *.test.ts suffix and mirror the source folder structure for clarity. Reuse helpers from tests/setup.ts when configuring shared mocks. Maintain or improve coverage when touching public features—verify locally with pnpm test:coverage and include regression cases for bug fixes.
Commit & Pull Request Guidelines
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.
- 9d ago First seen · 26 lines · 595 tokens per session scan A 937898331233
heroku-ai-provider AGENTS.md is an instructions file published in the GitHub repository julianduque/heroku-ai-provider (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 595 tokens to every session, about $0.0030 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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).
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.