What is feed-reader AGENTS.md?

A project-specific instruction file for psg2/feed-reader, a feed-reading application with a web app, a macOS app, a database server, and an MCP endpoint.

It is for working safely in the feed-reader codebase, including starting services, running development workflows, and understanding how its clients and server communicate.

It gives a coding agent the project’s architecture, development commands, environment rules, and file layout before it changes the code.

How psg2/feed-reader configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to psg2/feed-reader. 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/psg2/feed-reader/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/psg2/feed-reader

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/psg2/feed-reader/agents-md/github.svg)](https://agentmods.dev/instructions/psg2/feed-reader/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/psg2/feed-reader/agents-md"><img src="https://agentmods.dev/badge/instructions/psg2/feed-reader/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/psg2/feed-reader/agents-md"><img src="https://agentmods.dev/badge/instructions/psg2/feed-reader/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,323 This file is loaded in full into every session.

When invoked 2,323 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02323	$0.02323
Opus 5.5	$0.00929	$0.00929
Sonnet 5.5	$0.00465	$0.00465
Haiku 4.5	$0.00232	$0.00232

Measured 7d ago against content hash 01d4b7beb208, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

feed-reader AGENTS.md scanned grade C with 1 finding 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"buildCommand": "cd ../.. && if [ \"$VERCEL_ENV\" = \"production\" ]; then pnpm db:migrate; fi && pnpm build && rm -rf node_modules .pnpm-store apps/*/node_modules packages/*/node_modules tooling/*/node_modules"

AGENTS.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feed Reader — codebase guide

Single-user feed reader: TanStack Start web app on Vercel + Neon Postgres, a SwiftUI macOS client (macos/, see macos/README.md) and a remote MCP endpoint. The server is the source of truth; every client writes through to it.

Dev workflow

pnpm deps:up starts Postgres + pgweb in Docker and writes POSTGRES_URL / TEST_DATABASE_URL (Docker-assigned ports) into .env.docker. The dev, test and db scripts load it; never hardcode ports.
pnpm dev runs Vite behind portless at https://feedreader.localhost (apps/web/portless.json); worktrees get https://<branch>.feedreader.localhost. Escape hatch: cd apps/web && pnpm exec vite dev --port 3000.
A fresh clone runs with no .env.local (dev defaults in apps/web/lib/env.ts). .env.example lists every optional variable; docs/deploy.md explains them.

Stack

TanStack Start (Vite + Nitro, SSR) · TanStack Router (file-based) · TanStack Query + oRPC (contract-first) · BetterAuth (email/password, OTP, optional Google, API keys, OAuth 2.1 provider for the macOS app and MCP clients) · Postgres 17 + Drizzle · Tailwind v4 + shadcn/ui + Radix · Turborepo + pnpm · oxlint + oxfmt · Vercel. Sentry, PostHog and Axiom are wired but disabled without keys. VITE_PUBLIC_POSTHOG_KEY also turns on MCP Analytics for /api/mcp (server/mcp/analytics.ts): tool calls, agent intent, latency, errors and send_feedback reports (missing capabilities, confusing tools, praise), attributed to the user id, with tool arguments and results stripped before sending.

Commands

pnpm dev | build | preview
pnpm test                  # apps/web: vitest unit (real Postgres) + frontend (happy-dom)
pnpm test:db:migrate       # once after deps:up: migrate TEST_DATABASE_URL
pnpm test:e2e              # Playwright (apps/web/e2e)
pnpm lint | lint:fix | format | format:check | type-check | knip
pnpm db:generate | db:migrate | db:seed | db:reset | db:studio

Read the full file on GitHub · 94 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.

7d ago Changed · +1 lines · +53 tokens per session scan A → C 01d4b7beb208
16d ago Changed · +2 lines · +43 tokens per session 9d9c70f8d1a0
22d ago Changed · +1 lines · +503 tokens per session c06a48bdd61c
1mo ago Changed · +82 tokens per session 0ce487f739cd
1mo ago Changed · +64 tokens per session 92df56f2962d
2mo ago First seen · 90 lines · 1,578 tokens per session scan A cdb094c09eb4

Subscribe to this mod's changes

feed-reader AGENTS.md is an instructions file published in the GitHub repository psg2/feed-reader (0 stars, last pushed yesterday), licensed MIT. It adds 2,323 tokens to every session, about $0.0093 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

feed-reader AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
feed-reader AGENTS.mdpsg2/feed-reader	Instructions file	0	yesterday	MIT	C	2,323	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

feed-reader: Instructions file for Codex