effect-mcp: Instructions file for Codex

AGENTS.md

effect-mcp AGENTS.md is an instructions file for Codex, OpenCode from tim-smart/effect-mcp. It costs 3,645 tokens per session, scanned A, original, MIT.

Repository instructions for writing Effect code, where Effect is a TypeScript library for describing asynchronous work, failures, and related operations.

In plain words
What is it for?
Writing basic Effect programs and functions, using the Effect documentation search tool, and following the required setup and error-handling conventions.
Why use it?
They give an agent project-specific rules for using the Effect MCP server and writing Effect code in the expected style.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is tim-smart/effect-mcp's own configuration. It tells Codex and OpenCode how to work on effect-mcp 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 effect-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tim-smart/effect-mcp. 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/tim-smart/effect-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tim-smart/effect-mcp

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 effect-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tim-smart/effect-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/tim-smart/effect-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tim-smart/effect-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tim-smart/effect-mcp/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 effect-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tim-smart/effect-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tim-smart/effect-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,645 This file is loaded in full into every session.
When invoked 3,645 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 $0.03645 $0.03645
Opus 5.5 $0.01458 $0.01458
Sonnet 5.5 $0.00729 $0.00729
Haiku 4.5 $0.00364 $0.00364

Measured 2mo ago against content hash 25973e5c91d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

effect-mcp 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 2mo 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 · 472 lines

How it starts

The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Effect Guide

Pre-requisites

  • Have the Effect MCP server installed and running.
    • npx -y effect-mcp@latest

Critical information

Important: When requiring more information about Effect, use the effect_docs_search MCP tool. It is an authoritative source of information about Effect and its ecosystem.

Writing basic Effect's

Prefer Effect.gen when writing Effect's. It is a powerful way to create an Effect in a async/await style, which is more readable and maintainable.

import { Effect, Random } from "effect"

Effect.gen(function* () {
  // Use `yield*` to run another Effect
  yield* Effect.sleep("1 second")

  const bool = yield* Random.nextBoolean
  if (bool) {
    // When failing with Effect.fail/die etc. always use `return yield*` so
    // TypeScript can correctly narrow conditional types
    return yield* Effect.fail("Random boolean was true")
  }

  // You can return a success value directly
  return "Returned value"
}).pipe(
  // You can use the `pipe` method to add additional operations
  Effect.withSpan("tracing span"),
)

Writing Effect functions

If you need to write a function that returns an Effect, prefer using Effect.fn. It allows you to use the yield* syntax inside the function body, and also add a span for observability.

import { Effect, Random } from "effect"

const myEffectFn = Effect.fn("myEffectFn")(
  function* (x: number, y: number) {
    const bool = yield* Random.nextBoolean
    if (bool) {
      // When failing with Effect.fail/die etc. always use `return yield*` so
      // TypeScript can correctly narrow conditional types
      return yield* Effect.fail("Random boolean was true")
    }
    return x + y
  },
  // You can add "pipe" operations as additional arguments
  Effect.annotateLogs({
    some: "annotation",
  }),
  // You can also access the arguments of the function in pipe operations
  (effect, x, y) => Effect.annotateLogs(effect, { x, y }),
)

// call the Effect function
myEffectFn(1, 2).pipe(Effect.runPromise)

// You can also omit the function span name if you don't need it
const withNoSpan = Effect.fn(function* (x: number, y: number) {
  yield* Effect.log("Calculating sum", { x, y })
  return x + y
})

Read the full file on GitHub · 472 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. 2mo ago First seen · 472 lines · 3,645 tokens per session scan A 25973e5c91d6

Subscribe to this mod's changes

effect-mcp AGENTS.md is an instructions file published in the GitHub repository tim-smart/effect-mcp (238 stars, last pushed 8mo ago), licensed MIT. It adds 3,645 tokens to every session, about $0.0146 per session on Opus 5.5. 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.

Related

effect-mcp AGENTS.md compared with instructions from other repositories

effect-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
effect-mcp AGENTS.mdtim-smart/effect-mcpInstructions file2388mo agoMITA3,645Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode