caveman-plugin-dsh
Caveman voice for DSH (dsh-TUI) — terminal and web. Why use many token when few token do trick.
A dsh plugin that makes the agent answer terse: fragments over sentences,
fluff gone, every technical fact kept. It ships the
caveman voice skills, an always-on
system-prompt section, a /caveman toggle and a TUI badge.
- Plugin-only. No dsh core change, no patch, no fork. Plain Cordis services.
- Host-agnostic. Loads in the
tuiprofile and thewebprofile. - Subagent-safe. Delegated children keep full prose; only the root agent gets the voice.
- Zero dependencies. Plain ESM, no build step, no npm install, no network.
/caveman on # terse from now on
/caveman off # normal prose
/caveman status # current mode
Install
Requires dsh 0.17+ (plugin manifest v0.15). Clone, then add it to the profile(s) you use:
git clone https://github.com/farchanjo/caveman-plugin-dsh.git
dsh plugin --profile tui add ./caveman-plugin-dsh # terminal UI
dsh plugin --profile web add ./caveman-plugin-dsh # web UI
Restart dsh afterwards. Remove with dsh plugin --profile <p> remove caveman-plugin-dsh.
The manifest is validated by the host's own validatePlugin; it declares the
commands.dsh/v1alpha1#Command contract and the commands.invoke permission.
No grants file is needed: no mediated capability and no storage are used.
Usage
/caveman (or /caveman help) opens a text wizard in the footer:
1on 2off 3st 4cav 5ultra 6mega · 7jev+ 8jev- 9key- 10ls 11url 12key+ q
Type the number; the footer repaints with the new state and nothing is sent to
the model. q closes, any other text closes the menu and goes through as a
normal message. Prompts (key, endpoint, model pick) consume the next line
and stay open on a bad value, showing the reason inline; c cancels the prompt.
The menu expires after 120 s.
| Pick | Action | Pick | Action |
|---|---|---|---|
| 1 | voice on | 7 | jev on |
| 2 | voice off | 8 | jev off |
| 3 | status | 9 | clear key |
| 4 / 5 / 6 | level caveman / ultracave / megacave | 10 | list models |
| 11 | set endpoint | 12 | set key |
Direct verbs still work without the menu: /caveman on, /caveman off,
/caveman status, /caveman caveman|ultracave|megacave, /caveman jev on|off,
/caveman key <k>|clear, /caveman model [list|<id>], /caveman endpoint [<url>|reset].
Spoken phrases work too and never need a slash: "stop caveman", "normal mode", "talk like caveman", "be brief". A loose phrase ("pode voltar ao modo normal?") is disambiguated by the decision model before it is acted on.
Every change is persisted to the state file, so the mode, level and jev switch
survive a restart.
Decision model (optional)
Loose phrasing is classified before the plugin toggles anything. Deterministic
phrases never call it; only short messages that mention caveman/brief/normal-mode
do. The model is chosen by you — typesafe/jev-router out of the box, any
OpenRouter model via /caveman model, any OpenAI-compatible endpoint via
/caveman endpoint.
It fails open: no key, offline, timeout (1.5 s) or junk JSON means the exact heuristics still apply and the turn never waits longer than the timeout.
State file
~/.config/caveman-plugin-dsh/config.json — created on first run, directory
0700, file 0600, atomic writes. It holds the key, the model, the endpoint,
jev on/off, and the voice mode/level, so everything survives a restart.
{
"version": 1,
"mode": "on",
"level": "caveman",
"decision": true,
"model": "typesafe/jev-router",
"baseUrl": "https://openrouter.ai/api/v1",
"apiKey": "sk-or-…"
}
No environment variable is read. A corrupt file is moved to config.json.bak-<ts>
and regenerated; a file looser than 0600 logs a warning. The key is only ever
echoed masked.
Privacy: the candidate message and the current on/off state are sent to the configured endpoint, and only when a candidate is detected.
Configuration
Optional keys in the profile row's config:
| Key | Default | Meaning |
|---|---|---|
alwaysOn |
true |
initial voice mode when the file is first created |
decision.timeoutMs |
1500 |
hard cap per classification |
decision.apiKey |
– | inline key, wins over the file |
commands |
true |
register the /caveman command |
status |
true |
show the TUI badge |
- id: caveman-plugin-dsh
config:
alwaysOn: false
CAVE_DEBUG=1 appends scope/classify decisions to $TMPDIR/caveman-plugin-dsh.log.
Compatibility
| Host | Status |
|---|---|
dsh tui 0.17 |
works — voice, command, badge |
dsh web |
works — voice, command; no badge (the web has no tuiStatus) |
| subagents | excluded by design; their reports stay in full prose |
Scope of the port: this is the voice half of caveman. The input-compression proxy ("read less") has no dsh plugin seam today, so it is not included.
Layout
lib/index.js # the whole plugin (~270 lines, ESM, no build)
skills/caveman/SKILL.md # verbatim upstream skills
skills/ultracave/SKILL.md
skills/megacave/SKILL.md
rules/caveman-activate.md # verbatim upstream activation rule
dsh-plugin.json # manifest v0.15
cordis.patch.yml # profile-row insert
License
Plugin code: MIT (LICENSE). Skills and activation rule: Apache-2.0 ©
Julius Brussee — see NOTICE and
LICENSE-Apache. The combined work is MIT AND Apache-2.0.
No comments yet. Be the first to write one.