DSH Plugins Marketplace

DSH Plugins

Plugins

/

Workflow & Automation

/

dsh-prompt-gate

d

dsh-prompt-gate

Manifest valid

You type one line and the agent guesses the rest; this plugin rewrites that line into a complete prompt with goal, scope and acceptance criteria and waits for your go-ahead before the agent touches an

hasBundlePatch

dsh-prompt-gate

npm license dsh

Nobody teaches you how to talk to an agent. You open a new session, type one sentence, and dsh has to guess the rest.

dsh-prompt-gate stops the guessing. The first message is rewritten into a brief dsh can actually execute and shown to you as a card — and its tools stay locked until you approve.

中文


Why your first message is the problem

You typeWhat dsh has to guess
"take a look at this project"which part, for what, and what "done" means
"make the login page nicer"which files, which framework, whether markup is fair game

That guessing is where rework comes from — not from a weak model, but from a request that was never a prompt. The answer is not "go learn prompt engineering". It is one step before the work starts.

What it does

You type:

make the login page nicer

You get:

## Task
Upgrade the visual design of the login page in apps/web, keeping its route and copy untouched.

## Context
- apps/web/src/pages/login.tsx, styles in login.module.css
- design tokens in apps/web/src/styles/tokens.css

## Scope and constraints
- Styling only: no route, copy, or component-structure changes
- Reuse the existing tokens; introduce no new colors

## Deliverable and acceptance
- Renders at 375px and 1440px with no horizontal overflow
- `pnpm --filter web test` passes

## Suggested steps
1. Read login.module.css and tokens.css
2. Rework spacing and type scale first, then color

Two buttons sit under it. Approve starts the work under that brief. Type a change request into the answer field instead, and it rewrites and asks again — as many rounds as you like.

While the review is open, only read-only tools are callable (read, glob, grep, web_*), plus skill and ask_user_question.

Why a gate, not just a rewriter

A rewriter you can ignore is a suggestion. This is a gate: until the review settles, a tools.guard denies bash, write, edit and every other tool at the execution layer. The model cannot work around you, and it cannot claim you agreed.

Install

Requires dsh >= 0.2.2-alpha.2 (the sessionProjections, tools.guard and output.presentationMeta contracts this plugin relies on are pinned to that version; older releases are untested).

dsh plugin --profile web add dsh-prompt-gate                    # from npm
dsh plugin --profile web add github:tbx709/dsh-prompt-gate      # from GitHub

Or clone the repository and install the directory from Plugins → install_bundle. If the plugin row reports a load failure after installing, restart dsh once so it loads a fresh module generation.

This bundle is Host-only: no browser code, the card is rendered by dsh's own question panel, so no page refresh is involved.

Configuration

Override the row in the profile's cordis.patch.yml; every field is optional:

- id: prompt-gate
  config:
    scope: first        # first (default) | every
    timeoutMs: 900000
FieldDefaultMeaning
enabledtrueMaster switch.
scopefirstfirst: the opening turn only — existing conversations are never gated retroactively. every: every user message is reviewed.
timeoutMs900000Longest wait for an answer (15 min); on timeout the original message proceeds. 0 disables the timeout.
forceReviewfalseRefuse the "already clear, skip the card" path.
section''Extra guidance appended to the built-in protocol section.
header / questionChinese copyCard heading and question.
approve / skipChinese copyThe two button labels; they must differ.
approveHint / skipHintChinese copyButton tooltips.

How the gate works

No browser code and no private state machine — the gate is derived from the session log:

  • a promptGate session projection folds four numbers: first and last human message, the latest settled review, and the turn count;
  • a systemPrompt.section renders the protocol only while a review is open;
  • the review_prompt tool is admitted only while a review is open (its registration when);
  • a tools.guard denies every other tool meanwhile — monotonic, so no listener can turn a denial back into permission;
  • output.presentationMeta records {tool, outcome} in tool/result.meta, and that is what closes the gate. Restart, resume and plugin reload derive the same answer.

The only process-local state is the waiver for a model that never opens the review at all; it, too, is re-derived from the log.

Status

  • Automated: npm test drives apply against a fake Cordis host — gate derivation (first message, every message, old sessions, ineligible sessions), guard decisions, the four card answers, timeout, forceReview, config validation.
  • Exercised by hand: the author on dsh 0.2.2-alpha.2 in the Web UI.
  • Untested: any other dsh release, and headless/CLI environments (with no question channel the plugin steps aside and gates nothing).

Limits

  • Forked sessions and subagent sessions never trigger.
  • scope: first covers the opening turn only; a conversation already past its second turn is never gated retroactively.
  • scope: every also applies to existing sessions, but only to messages sent after it was enabled. Steering mid-turn counts as a message and asks for a review too.
  • Closing the card is the same as choosing "use the original".
  • There is no question channel in a pure CLI or headless profile, so nothing is gated there.

Development

Plain JavaScript, no dependencies, no build step.

npm run check   # node --check index.js
npm test        # fake-host smoke test
index.js                    host plugin: config, projection, prompt section, guard, review_prompt tool
cordis.patch.yml            bundle patch (inserts one row)
locale/{zh,en}.json         Plugin Manager title and description
icon.svg                    icon
test/plugin.test.mjs        logic test against a fake Cordis context

License

MIT

Comments

Loading…

Similar plugins

dsh-prompt-booster

by haidashu79-prog

For non-expert users who struggle to write clear prompts: on every message the plugin (agent/pre-step hook) auto-completes the vague/incomplete input into a full instruction with goal/constraints/deli

Tools & CapabilitiesManifest valid

★ 0

JavaScript

Nov 15, 2026

dsh plugin --profile web add dsh-prompt-booster

by caishengshuo

Every file, one version before it breaks. A DSH plugin: snapshots a file the instant before an agent rewrites it, with a per-session GUI timeline where any point can be restored in one click.

Terminal & ClientsManifest valid

★ 0

MIT

JavaScript

Oct 24, 2026

dsh plugin --profile web add dsh-beforewrite

A row of quick-phrase buttons in the DSH composer: one click sends "please continue" or any saved phrase, so a stalled agent keeps working without touching your draft.

UI & ExperienceManifest valid

★ 0

dsh plugin --profile web add dsh-plugin-quick-resume

One-click prompt polisher for the DSH composer: a ✨ button next to the message box opens a side-chat where an agent refines your rough draft over multiple turns, then you copy the result back. Replays

Workflow & AutomationTerminal & ClientsManifest valid

★ 0

dsh plugin --profile web add narrative-prompt-polish

by meng-lx

Restart initiated by the agent itself, not by a button. The agent calls one tool, then the plugin takes over: it waits until every agent and background job on the host is idle, runs a visible ten-seco

Sessions & MessagesManifest valid

★ 0

MIT

JavaScript

Nov 9, 2026

dsh plugin --profile web add dsh-autonomous-restart

by TCY07

Keeps an agent working continuously over long stretches: set a deadline, and if it finishes the task early, Dont-Stop automatically nudges it to keep iterating and take on the next step on its own.

Workflow & AutomationDevelopment & InfrastructureManifest valid

★ 1

MIT

JavaScript

Nov 2, 2026

dsh plugin --profile web add dsh-dont-stop