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.
npx agentmods add instructions/mpsuesser/effect-claudecode/agents-mdgit clone --depth 1 https://github.com/mpsuesser/effect-claudecodeWrote 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.
[](https://agentmods.dev/instructions/mpsuesser/effect-claudecode/agents-md)<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>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 | $0.02472 | $0.02472 |
| Opus 5 | $0.01236 | $0.01236 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
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 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.
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.
- 3d ago First seen · 179 lines · 2,472 tokens per session scan C 17ded17a0ffe
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.
Other instructions, from other repositories
avoid-ai-writing CLAUDE.md
Instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
imgui-java CLAUDE.md
Instructions for SpaiR/imgui-java: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
rolecraft AGENTS.md
Instructions for rolecraft-sh/rolecraft, covering rolecraft — development guidelines, ⚠️ startup checklist (read before every task), workflow, interaction rules and code style.
claude-omakase CLAUDE.md
Instructions for gyuch-an02/claude-omakase, covering claude.md, commands, architecture (the big picture), conventions and out of scope.
pencil-skill AGENTS.md
Instructions for Nisus74/pencil-skill, covering pencil-dev-skill: project context, project purpose, naming conventions, repository structure and project context files.