agentleFS
Sign inStart free
thenickzthenickz/opencode-notify/AGENTS.md

opencode-notify

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

Notifications for opencode: OS desktop + optional Telegram on question, permission, and response-finished events. Ships an opencode plugin, a cross-platform shell dispatcher, and a portable Agent Skills notify skill.

  • Reads credentials
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep README.md, skills/notify/SKILL.md, and this file in sync when behavior or config changes.

    line 32
  2. Very specific:

    Never store tokens in docs or logs.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

opencode-notify

Notifications for opencode: OS desktop + optional Telegram on question, permission, and response-finished events. Ships an opencode plugin, a cross-platform shell dispatcher, and a portable Agent Skills notify skill.

Stack

  • Plugin: JavaScript (ESM, zero deps — Bun fetch, $, SDK client only).
  • Dispatcher: Bash (scripts/notify.sh), no external deps beyond the OS's native notify tool (notify-send, osascript, PowerShell BurntToast).
  • Skill: Agent Skills format (skills/notify/SKILL.md, name + description frontmatter).

Commands

EXACT and verified commands.

  • Install (symlinks plugin + dispatcher + skill): ./install.sh
  • Preview: ./install.sh --dry-run
  • Remove symlinks: ./install.sh --unlink
  • Validate plugin syntax, dispatcher syntax, and skill frontmatter: ./scripts/validate.sh
  • OS dispatcher smoke test: ~/.config/opencode/notify.sh "opencode" "test" done
  • Live plugin trace: run opencode with OPENCODE_NOTIFY_DEBUG=1, log at /tmp/opencode/notify-debug.log

Conventions

  • Plugin env vars: OPENCODE_NOTIFY_* (OS/channel) and OPENCODE_TELEGRAM_* (Telegram). Every event toggle defaults to ON; =0 disables.
  • Config resolution at plugin load: ~/.config/opencode/opencode-notify.env (canonical, wins) over process.env (shell/~/.bashrc fallback). The file is read directly, so edits apply even from a stale parent shell; a restart is still required. Missing/empty file ⇒ current (env-only) behavior.
  • Config file format: one KEY=value per line, # comments, optional export prefix and surrounding quotes; no inline comments. install.sh creates a commented template if missing and keeps it chmod 600.
  • Keep README.md, skills/notify/SKILL.md, and this file in sync when behavior or config changes.
  • The plugin resolves notify.sh from $HOME/.config/opencode/notify.sh first, then ../scripts/notify.sh relative to the plugin's realpath — keep that fallback.
  • Never store tokens in docs or logs; keep them in env vars or the private opencode-notify.env (chmod 600) only.

Structure

plugins/opencode-notify.js   opencode plugin (events → notify, env-file config)
scripts/notify.sh            OS dispatcher (auto-detect platform)
scripts/notify-env-test.mjs  unit tests for the plugin's config-file parser
skills/notify/SKILL.md       portable skill (setup + config + self-diagnosis)
install.sh                   symlink installer (non-destructive, --dry-run/--unlink)
scripts/validate.sh          syntax + parser + frontmatter checks

Boundaries

  • install.sh never overwrites existing config (skips with a warning).
  • OS channel is silent by default; failures only print with OPENCODE_NOTIFY_DEBUG=1.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free