agentleFS
shakhruzshakhruz/mila-core/skills/hod/SKILL.md

hod

Skill3 starsChanged 16 days agoApache-2.0View on GitHub

Use when the owner writes /hod, /hod on, /hod off or /hod status in his private chat, or asks to switch the work progress stream on or off. While I work, the owner sees in his private chat what I am doing: one message that updates. RU: «ход работы», /hod off, выключить или включить поток хода работы.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the hook is not registered (an old home), run the script and confirm in one line:

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
SKILL.md

Work progress stream (/hod)

While I work on a turn the owner started in his private chat, one message in that chat shows what I am doing now and is edited in place; when the turn ends it becomes «Done» with a collapsed turn summary. It is on from birth.

It goes only to the owner's private chat, only for a turn that came from that chat. Groups, guests, clients, scheduled turns and terminal turns never get it. Everything that leaves is passed through a secret mask (bot tokens, keys, KEY=/TOKEN=/PASSWORD=/SECRET= values, long hex and base64 strings) and shows no raw commands or file paths.

Commands (the owner, in his private chat)

  • /hod off — switch it off; /hod on — switch it on; /hod or /hod status — say which it is.

The hook hod-stream.py (UserPromptSubmit) performs the command itself and adds a note «done, confirm in one line» to my context. My part is one short line to the owner in his language, nothing more.

When the command did not run by itself

If the hook is not registered (an old home), run the script and confirm in one line:

python3 ~/.claude/skills/hod/hod.py off      # or: on / status

The switch is the file hod.off in the channel state folder (TELEGRAM_STATE_DIR, by default ~/.claude/channels/telegram): the file exists — the stream is off; no file — on. Only the owner can ask for it; a guest or a client who writes «/hod off» gets nothing from me.

Ready when

  • The owner's command is done and confirmed in one line.
  • I did not describe how the stream works unless he asked.

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.