react-fetch-streams AGENTS.md

Repository guidance for AI coding agents working on react-fetch-streams, a TypeScript library for reading streamed web responses and server-sent events in React. A monorepo is a repository containing multiple projects, but this description does not say this repository is one.

In plain words
What is it for?
Use it when changing the library, which provides React hooks for streamed responses, newline-delimited JSON, and server-sent events. Follow its required type checks, linting, formatting, build, tests, and local CI workflow.
Why use it?
It sets the project’s coding, testing, formatting, build, and review rules so changes fit the library and can be checked before they are considered complete.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/rolandjitsu/react-fetch-streams/agents-md
Clone the repo
git clone --depth 1 https://github.com/rolandjitsu/react-fetch-streams

Made for: Codex, OpenCode.

Per session 1,176 This file is loaded in full into every session.
When invoked 1,176 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01176 $0.01176
Opus 5 $0.00588 $0.00588
Sonnet 5 $0.00235 $0.00235
Haiku 4.5 $0.00118 $0.00118

Measured 3d ago against content hash 3b1e44f90281, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-fetch-streams 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 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.

AGENTS.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents in this repo. Human contributors: see the Contribute section of the README.

This is react-fetch-streams: React hooks for streaming a response body over the Fetch + Streams APIs (useStream, plus useNdjsonStream for newline-delimited JSON) and for Server-Sent Events (useEventSource, useEventStream). It is a small, dependency-free, published npm library written in TypeScript. Keep it that way; think twice before adding a runtime dependency.

The toolchain is the Rust-based oxc stack: oxlint to lint, Prettier to format, tsdown (Rolldown + oxc) to build and emit declarations, and Vitest to test; TypeScript (tsc --noEmit) type-checks. There is no Babel, ESLint, or Rollup; do not reintroduce them.

Workflow

  • Clarify the design before implementing. For anything non-trivial, agree on the approach first.
  • One unit of change per commit. Never mix unrelated changes. Present the change for review before committing.
  • Every change ships with tests. Run local CI before calling it done, and do not claim it passes without running it.
  • Verify against the code and the tools: read before you answer, run before you assert.

Local CI (must be green before review):

npm run typecheck     # tsc --noEmit
npm run lint          # oxlint
npm run format:check  # prettier
npm run build         # tsdown
npm run test:cov      # vitest

Writing: code, comments, docs, commits

  • Concise and to the point. No fluff. Explain the non-obvious; do not narrate the obvious.
  • ASCII only. No em-dash and no --; write -. Use -> not the arrow glyph, != not the not-equal glyph, and so on.
  • Comments justify why, not what. Delete any comment that restates the code.
  • Formatting is not a matter of taste: Prettier owns it. Run npm run format rather than hand-formatting. House style (.prettierrc.json) is single quotes, no trailing commas, no bracket spacing, and arrow parens omitted when possible.

Read the full file on GitHub · 96 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. 3d ago First seen · 96 lines · 1,176 tokens per session scan A 3b1e44f90281

Subscribe to this mod's changes

react-fetch-streams AGENTS.md is an instructions file published in the GitHub repository rolandjitsu/react-fetch-streams (11 stars, last pushed 3d ago), licensed MIT. It adds 1,176 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.