echook AGENTS.md

An operating guide for echook, a tool that connects AI coding agents with editor events and automated hooks. It documents supported platforms, hook events, matching rules, and the project’s testing and release practices.

In plain words
What is it for?
Use it when working on echook integrations, hook configuration, editor support, tests, continuous integration, or version updates.
Why use it?
It gives agents one reference for how echook behaves across editors and what to check before treating a task as 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/chanmeng666/echook/agents-md
Clone the repo
git clone --depth 1 https://github.com/ChanMeng666/echook

Made for: Codex, OpenCode.

Per session 2,720 This file is loaded in full into every session.
When invoked 2,720 The same file — it is already loaded in full.
Security scan C 2 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 $0.02720 $0.02720
Opus 5 $0.01360 $0.01360
Sonnet 5 $0.00544 $0.00544
Haiku 4.5 $0.00272 $0.00272

Measured 2d ago against content hash e519d3e4263a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

echook AGENTS.md scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

5. **AI-agent-first: no human-interactive paths.** Every operation is a non-interactive `audio-hooks` subcommand (JSON in, JSON out) or a non-interactive script. There are **no** human menus, prompts, or `curl | bash` fl

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. **AI-agent-first: no human-interactive paths.** Every operation is a non-interactive `audio-hooks` subcommand (JSON in, JSON out) or a non-interactive script. There are **no** human menus, prompts, or `curl | bash` fl
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

echook — AI Operator Guide

v6.4.0 · Multi-platform: Claude Code (plugin) · Cursor (native + auto-bridge) · Codex (plugin + native). Source-of-truth for every capability is audio-hooks manifest (live JSON, includes pointers, editor_targets, supported_editors). This file is orientation only.

Read the full file on GitHub · 71 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. 2d ago First seen · 71 lines · 2,720 tokens per session scan C e519d3e4263a

Subscribe to this mod's changes

echook AGENTS.md is an instructions file published in the GitHub repository ChanMeng666/echook (86 stars, last pushed 10d ago), licensed MIT. It adds 2,720 tokens to every session, about $0.0136 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.