dshbase

Plugin directory / AI Models / dsh-prompt-rail

dsh-prompt-rail

Verified · install-tested on dsh Zzzzkd

✓ Actively maintained Builds on 6 official DSH packages Pure TypeScript

View on GitHub ↗ ← Back to plugin directory

7Stars
0Forks
1Open issues
TypeScriptLanguage
2026-08-15Last push
Cross-platformPlatform

What it does

Prompt Rail is a compact vertical prompt quick-jump bar for DeepSeek Harness web session pages. Each bar corresponds to a currently loaded normal user prompt. Hover or keyboard focus shows preview; click scrolls to the corresponding prompt.

✅
Our take
Works — verified, early-stage project

Prompt Rail is a compact vertical prompt quick-jump bar for DeepSeek Harness web session pages. Each bar corresponds to a currently loaded normal user prompt. Hover or keyboard focus shows preview; click scrolls to the corresponding prompt. It installs cleanly and boots without issues in our testing. It's early-stage but functional.

“Verified” means our automated CI actually ran dsh plugin add in a clean profile and it booted — nothing more. Feature descriptions and version compatibility are the author’s claims. This is not a security audit and not an endorsement of third-party code.

README

DSH Prompt Rail

English | 锟斤拷锟斤拷

Prompt Rail is a compact vertical quick-jump rail for the DeepSeek Harness Web conversation view. One mark represents one loaded ordinary user prompt. Hover or keyboard focus shows its preview; clicking scrolls to that prompt.

Prompt Rail

Behavior

  • The rail stays vertically centered beside the session sidebar.
  • Every mark has a 10px high hit slot, while its default visible mark is an 8px by 3px light line.
  • Hover/focus makes the current mark 28px wide and dark; nearby marks taper to 20px, 14px, and 10px.
  • Clicking records the selected prompt. When the pointer leaves, all marks return to their default length while the selected mark stays dark.
  • Assistant, tool, command, steering, and injected-context rows are excluded. A one-prompt conversation still renders one mark.

Install

Clone or copy this repository into the Harness root plugins directory:

deepseek-harness/
锟斤拷锟斤拷 plugins/
   锟斤拷锟斤拷 dsh-prompt-rail/

Then open a terminal in the deepseek-harness root and run:

Windows

.\plugins\dsh-prompt-rail\install-and-restart.bat

macOS / Linux

node ./plugins/dsh-prompt-rail/compat/install.mjs
pnpm dsh web

Keep the plugins/dsh-prompt-rail directory after installation.

Development

The development layout expects sibling checkouts:

workspace/
锟斤拷锟斤拷 dsh/                       # DeepSeek Harness checkout
锟斤拷锟斤拷 dsh-prompt-rail/

Then run:

pnpm install
pnpm run check

lib/ is committed because profile installation loads the prebuilt Host and browser files without running package build scripts.

Release checklist

  1. Add an exact compatibility patch for every supported pre-slot Harness revision.
  2. Run pnpm run check and exercise node compat/install.mjs --apply-only in a clean matching checkout.
  3. Commit source, lib/, compat/, README files, screenshot, and lockfile.
  4. Push a v0.1.0 tag and create a GitHub Release from that tag.
  5. State the compatible Harness versions and revision hashes in the release notes.

License

MIT

Install

🧩 Let your agent install it (recommended)

Install the catalog once, then DeepSeek Harness can find and install any plugin from this site automatically:

dsh plugin add dshbase-catalog

Then say "install dsh-prompt-rail for me" — your agent finds it in the directory and installs it. Docs: dshbase-catalog · verified packs.

This plugin is GitHub source (not published to npm) — install it straight from the repo:

Web profile:

dsh plugin --profile web add github:Zzzzkd/dsh-prompt-rail

Headless (CLI) profile:

dsh plugin --profile headless add github:Zzzzkd/dsh-prompt-rail

Test report

Verified: L1 install + L2 load + L3 runtime from GitHub source on dsh 0.1.0-rc.6.

When to use it

Bring a new model, provider, or routing policy into the loop so dsh can pick the right brain for the job.

Who it's for

Users juggling multiple models or providers who want cost, quality, and latency balanced automatically.

For developers — extending it

Provider adapters and routing heuristics are the seams — add a backend, tune the fallback chain, or add per-task model selection.

Security: not yet scanned — our daily static scan will cover it shortly.

Share this badge

More in AI Models

Browse all 7797 plugins →