echook: Instructions file for Codex

AGENTS.md

echook AGENTS.md is an instructions file for Codex, OpenCode from ChanMeng666/echook. It costs 1,660 tokens per session, scanned A, original, MIT.

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

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

This is ChanMeng666/echook's own configuration. It tells Codex and OpenCode how to work on echook 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 echook configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ChanMeng666/echook. 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/ChanMeng666/echook/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ChanMeng666/echook

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 echook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chanmeng666/echook/agents-md/github.svg)](https://agentmods.dev/instructions/chanmeng666/echook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/chanmeng666/echook/agents-md"><img src="https://agentmods.dev/badge/instructions/chanmeng666/echook/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 echook AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chanmeng666/echook/agents-md"><img src="https://agentmods.dev/badge/instructions/chanmeng666/echook/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,660 This file is loaded in full into every session.
When invoked 1,660 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 $0.01660 $0.01660
Opus 5.5 $0.00664 $0.00664
Sonnet 5.5 $0.00332 $0.00332
Haiku 4.5 $0.00166 $0.00166

Measured 7d ago against content hash 7dd33adbcd2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

echook 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

echook — agent guide

echook does two things for Claude Code, Cursor and Codex: (1) audio and out-of-band notification of editor lifecycle events (sound, spoken summary, desktop toast, webhook) and (2) the status line. Live truth for every subcommand, hook, config key, error code and env var is audio-hooks manifest; this file only holds what that JSON and the code cannot tell you.

Map

Path What it is
hooks/ Runtime, flat modules. hook_runner.py is the entry: event tables, gating (enabled, snooze, filters, debounce), run_hook, main. runner_core.py owns shared state (preferences handle, NDJSON log, queue dir, invoker lookup). One concern each: audio_playback.py, desktop_notification.py, text_to_speech.py, webhook_dispatch.py, rate_limit_alerts.py, terminal_sequence.py, notification_context.py (wording, sanitising), platform_shell.py (PowerShell launch and escaping, WSL). Call across modules as module.name(...), never from module import name. Also user_preferences.py (config load, migration, data-dir resolution) and invoker.py (which editor called).
bin/ audio-hooks.py is the CLI entry: dispatch, config, state detection, small commands, manifest. Larger concerns are one module each in bin/echook_cli/ (legacy_uninstall, editor_installs, statusline, plugin_upgrade, config_backup, error_codes, …; its __init__.py lists them). Add a concern as a new module there, not to the entry file. Also the two status-line renderers and the launchers.
config/ default_preferences.json (the template every install migrates toward), audio_manifest.json (prompt per sound file).
audio/default/, audio/custom/ Voice theme and chime theme; one file per event and variant.
cursor-hooks/, codex-hooks/ Install templates for those editors.
plugins/audio-hooks/ The shipped plugin. Its audio, bin, config, cursor-hooks, codex-hooks directories and the Python files in its hooks directory are a build mirror — never edit. Hand-edited in place: plugins/audio-hooks/hooks/hooks.json (the Claude Code registration; no repo-root counterpart), runner, skills, evals, README.md and the two plugin manifests.
scripts/ build-plugin.sh, bump-version.sh, generate-audio.py. The script installer was removed in 7.0.0; audio-hooks uninstall still removes an old script install.
tests/ unittest suite; every module imports _isolation first.

Read the full file on GitHub · 59 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. 7d ago Changed · +37 tokens per session 7dd33adbcd2a
  2. 15d ago Changed · -60 lines · -8,924 tokens per session scan C → A 01a207424678
  3. 20d ago Changed · +2 lines · +486 tokens per session 3edd03fdbd13
  4. 24d ago Changed · +33 lines · +6,317 tokens per session 5431e6d6e3e6
  5. 1mo ago Changed · +13 lines · +1,024 tokens per session 34484201681c
  6. 1mo 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 (90 stars, last pushed 7d ago), licensed MIT. It adds 1,660 tokens to every session, about $0.0066 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

Other instructions, from other repositories