effect-claudecode AGENTS.md

effect-claudecode AGENTS.md is an instructions file for Codex, OpenCode from mpsuesser/effect-claudecode. It costs 2,472 tokens per session, scanned C, original, MIT.

Repository instructions for effect-claudecode, a TypeScript library for building Claude Code hooks, plugins, skills, commands, and settings.

In plain words
What is it for?
Finding the right source files and running the full test suite, individual tests, or TypeScript checks.
Why use it?
They document the project layout and the commands needed to test and type-check changes.

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/mpsuesser/effect-claudecode/agents-md
Clone the repo
git clone --depth 1 https://github.com/mpsuesser/effect-claudecode

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-claudecode AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mpsuesser/effect-claudecode/agents-md.svg)](https://agentmods.dev/instructions/mpsuesser/effect-claudecode/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mpsuesser/effect-claudecode/agents-md"><img src="https://agentmods.dev/badge/instructions/mpsuesser/effect-claudecode/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,472 This file is loaded in full into every session.
When invoked 2,472 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02472 $0.02472
Opus 5 $0.01236 $0.01236
Sonnet 5 $0.00494 $0.00494
Haiku 4.5 $0.00247 $0.00247

Measured 3d ago against content hash 17ded17a0ffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

effect-claudecode 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 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.

Recursive force deletehighDestructive command

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

bunx vitest run -t "denies rm -rf" # by test name pattern
AGENTS.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — effect-claudecode

Effect-first library for writing Claude Code hooks, plugins, skills, subagents, commands, and settings in a maximally Effect-native way. Wraps Claude Code's extensibility primitives (stdio hook processes, settings.json, plugin manifests, frontmatter files, .mcp.json) in Effect v4 idioms.

Build / Lint / Test Commands

bun run test           # vitest run (all tests)
bun run typecheck      # tsc --noEmit

Running a single test

bunx vitest run test/Hook/Events/PreToolUse.test.ts     # single file
bunx vitest run -t "denies rm -rf"                        # by test name pattern
bunx vitest run test/Hook/Runner.test.ts -t "schema decode"

Verification before submitting

bun run test && bun run typecheck

Project Structure

src/
  index.ts                  Barrel: re-exports Hook, Settings, Plugin, Frontmatter,
                            Mcp, Testing namespaces + cross-module errors.
  Hook.ts                   Re-export hub for all Hook/* modules.
  Hook/
    Runner.ts               Hook.runMain + Hook.dispatch. Stdio FFI boundary.
    Context.ts              HookContext namespace (ServiceMap.Service + accessors).
    Envelope.ts             Base HookEnvelope schema (session_id, cwd, etc.).
    Matcher.ts              Tool-name regex helpers for Pre/PostToolUse.
    Transcript.ts           FileSystem-backed transcript reader.
    Events/
      index.ts              Builds HookInput/HookOutput tagged unions.
      <EventName>.ts        One file per event — Input, Output, decision
                            helpers, and define(). 27 event files total.
  Settings.ts               Re-export hub for Settings/*.
  Settings/                 SettingsFile schema + Settings.load (user/project/local merge).
  Plugin.ts                 Re-export hub for Plugin/*.
  Plugin/                   plugin.json manifest schema + Plugin.define + Plugin.write.
  Frontmatter.ts            Re-export hub for Frontmatter/*.
  Frontmatter/              YAML-frontmatter parsers for skills, subagents, commands.
  Mcp.ts                    Re-export hub for Mcp/*.
  Mcp/                      .mcp.json schema (stdio/http/sse discriminated).
  Errors.ts                 All Schema.TaggedErrorClass declarations.
  Testing.ts                Test helpers: runHookWithMockStdin, fixtures,
                            expect*Decision assertions.

test/                       One file per source module.
vitest.config.ts            vitest config (plain vitest, no vite-plus in Phase 1).
vitest.setup.ts             @effect/vitest equality testers.
tsconfig.json               Strict TS with @effect/language-service plugin.

Read the full file on GitHub · 179 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 · 179 lines · 2,472 tokens per session scan C 17ded17a0ffe

Subscribe to this mod's changes

effect-claudecode AGENTS.md is an instructions file published in the GitHub repository mpsuesser/effect-claudecode (9 stars, last pushed 2mo ago), licensed MIT. It adds 2,472 tokens to every session, about $0.0124 per session on Opus 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.