summerfi-monorepo: Instructions file for Codex

AGENTS.md

summerfi-monorepo AGENTS.md is an instructions file for Codex, OpenCode from OasisDEX/summerfi-monorepo. It costs 10,729 tokens per session, scanned A, original, Apache-2.0.

Project instructions for OasisDEX's Summerfi monorepo, a single repository containing multiple related packages and applications. They explain how the packages connect and provide checklists for changes that cross package boundaries.

In plain words
What is it for?
Use them when changing shared SDK code, adding services or protocol plugins, or making changes that affect several workspaces.
Why use it?
They reduce the risk of updating one package while missing the clients, services, or applications that depend on it. They also document the repository's package structure and conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md.

This is OasisDEX/summerfi-monorepo's own configuration. It tells Codex and OpenCode how to work on summerfi-monorepo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything summerfi-monorepo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to OasisDEX/summerfi-monorepo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/OasisDEX/summerfi-monorepo/dev/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/OasisDEX/summerfi-monorepo

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for summerfi-monorepo AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oasisdex/summerfi-monorepo/agents-md/github.svg)](https://agentmods.dev/instructions/oasisdex/summerfi-monorepo/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/oasisdex/summerfi-monorepo/agents-md"><img src="https://agentmods.dev/badge/instructions/oasisdex/summerfi-monorepo/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.

agentmods 80×15 button for summerfi-monorepo AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oasisdex/summerfi-monorepo/agents-md"><img src="https://agentmods.dev/badge/instructions/oasisdex/summerfi-monorepo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,729 This file is loaded in full into every session.
When invoked 10,729 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.10729 $0.10729
Opus 5 $0.05365 $0.05365
Sonnet 5 $0.02146 $0.02146
Haiku 4.5 $0.01073 $0.01073

Measured 9d ago against content hash a5b284dfef3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

summerfi-monorepo 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.

AGENTS.md · 537 lines

How it starts

The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Package Change Checklists

This file maps out how the workspaces in this monorepo connect, and gives ordered checklists for common changes that span multiple packages. File paths are relative to the repo root.

Package Map

  • SDK layering (sdk/) — domains are split into <domain>-common (interfaces/types only, e.g. tokens-common exports ITokensManager/ITokensProvider) and <domain>-service (a factory + concrete implementation, e.g. TokensManagerFactory.newTokensManager). Consumers depend on the -common contracts; sdk/sdk-server composes all the service factories into a per-request tRPC context (sdk/sdk-server/src/context/SDKContext.ts) and exposes them via the sdkAppRouter route tree (sdk/sdk-server/src/SDKAppRouter.ts). sdk/sdk-client (and sdk-client-react) wrap those tRPC procedures in client manager classes hung off SDKManager (makeSDK), giving apps end-to-end types from the exported SDKAppRouter type.
  • Frontend apps (apps/)earn-protocol, earn-protocol-institutions and earn-protocol-landing-page consume the SDK client plus the shared packages/app-* libraries (app-types holds the SupportedNetworkIds/SupportedSDKNetworks switchboard enums, app-earn-ui the component library and chain/icon maps, app-server-handlers the server-side data fetchers, app-utils helpers). Per-fleet presentation comes from a remote JSON config (CONFIG_URL_EARN), not from code.
  • Lambdas + stackssummerfi-api/*, external-api/* and background-jobs/* are Lambda handler packages built on packages/serverless-shared (canonical ChainId/Network registry, response helpers). They are deployed by SST: sst.config.ts wires stacks/summer-stack.ts (main API) and stacks/partners-stack.ts (partner gateway); each feature has an add<Feature>Config module in stacks/. The SDK has its own SST app under sdk/.
  • Subgraph clients — the subgraphs themselves are deployed from other repos; this repo only holds typed client packages. Legacy clients (aave-spark-, ajna-, automation-, morpho-blue-, prices-, summer-events-subgraph) codegen from a checked-in schema.graphql; the summer-earn-*-subgraph clients codegen by introspecting the live endpoint. All resolve endpoints at runtime as ${SUBGRAPH_BASE}/<subgraph-name> via per-chain name maps. SDK-side, subgraph-manager-service reads SDK_SUBGRAPH_CONFIG.
  • Env vars — the SDK's ConfigurationProvider only loads keys listed in turbo.json globalEnv (and the SST stack config in sdk/sst-environment.ts); lambdas read process.env injected by the stacks/ modules from ../.env.
  • Databasespackages/summer-protocol-db, summer-institutions-db and summer-beach-club-db are Kysely clients with migrations; consumers pass connection strings from env (e.g. EARN_PROTOCOL_DB_CONNECTION_STRING).
  • Contractsarmada-protocol/abis (+ contracts submodule) for Armada v2; packages/core-contracts + deployment-configs for the legacy operations system.

Read the full file on GitHub · 537 lines

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.

  1. 9d ago First seen · 537 lines · 10,729 tokens per session scan A a5b284dfef3b

Subscribe to this mod's changes

summerfi-monorepo AGENTS.md is an instructions file published in the GitHub repository OasisDEX/summerfi-monorepo (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 10,729 tokens to every session, about $0.0536 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens