DSH Marketplace
中文

forkprobe

Jayden-X-L/forkprobe

Compare multiple skills on the same task and pick the winner.

673PythonMITSource

Install

Add forkprobe to DeepSeek Harness

via GitHub · GitHub source

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

What happened when we ran it

Installed cleanly when we ran it

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run yesterday.

Due diligence

Before you install forkprobe

  • Source of record: Jayden-X-L/forkprobe — present in the community registry that DSH's own plugin market installs from.
  • Licensed under MIT.
  • Detected: terminal surface. Read the source before granting these.
  • A listing here is not a security review. Plugins run with your agent's permissions.

The AI take

What it is — forkprobe is an AI skill selection tool. It runs multiple skills in parallel on the same task, generates a local HTML report, and lets you choose the winner.

Who it is for — When you are unsure which skill fits the current task and want to review real outputs before deciding, forkprobe is suitable to install. People who do not need skill comparison for simple deterministic tasks do not need to install it, because the answer or tool path is already clear and direct execution is faster.

Watch out — Installing forkprobe from GitHub source requires manually allowing the build script. Sandbox testing passed: it installs in a fresh profile and registers into the profile via Harness. No obvious issues found.

The verdict — I would install it because it generates continuation handoff after selecting the winner and supports anonymous sharing of the choice.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What forkprobe does

Parallel task paths are compared and converge into one selected result with a local report.

forkprobe is a DeepSeek Harness plugin that compares several skills on the same task and helps select a winner. It runs a baseline and multiple candidate skills with the same input, then opens a local HTML report containing the outputs, elapsed time, estimated token use, file previews and AI review suggestions. In DSH, the native forkprobe_compare tool starts candidate subagents in parallel. After selection, the report’s “Continue” action creates a local handoff and returns the chosen result so the current agent can continue with the winning skill.

Candidates can come from the local installed-skill set, EverMind Skill Hub, GitHub or a BYO path. The repository also documents direct runs with python3 scripts/compare.py, using options such as --input, repeated --skill, --judge and --output. The plugin scans local skills, removes duplicates and can optionally support anonymous winner sharing.

This is intended for tasks where output quality or artifact quality is uncertain, including writing, PPTX, figures, research reports, web pages and video. It is a poor fit for simple, deterministic work where the correct tool path is already clear. External GitHub candidates still require checks for licence, dependencies and output paths. The terminal surface reaches the environment to run comparison scripts and candidate pipelines, which may create reports and generated files with the agent’s permissions; the README does not describe an additional isolation layer. DSH users do not need a nested dsh process, and the plugin does not copy DSH credentials.

forkprobe documentation

How it behaves

forkprobe treats skill selection as a comparison run. It recommends a small candidate set, runs baseline and the selected skills with identical input, and writes a local HTML report. Depending on the task, the report can include text, previews, source files, QA results, media metadata, estimated token use, elapsed time and AI review comments. The documented workflow ends with a user-selected winner and a continuation handoff.

In DSH, the native forkprobe_compare tool starts candidate subagents in parallel. The README states that this native implementation does not launch a second dsh process or copy DSH credentials. It also retains installation confirmation, local Skill scanning, candidate de-duplication and optional anonymous winner sharing.

Commands

The README shows a direct comparison command:

python3 scripts/compare.py --input /tmp/forkprobe-input.txt --skill baseline --skill writing-anti-ai --skill humanizer-zh --skill remove-ai-flavor-writing-skill --judge --output /tmp/forkprobe-report.html

--input takes an input file, --skill can be supplied for each candidate, --judge enables the documented AI review step, and --output specifies the report path. The DSH-native tool is named forkprobe_compare; its full argument schema is not included in the supplied README.

Candidate sources and outputs

Candidates may be recommended from the curated directory, locally installed Skills, EverMind Skill Hub, GitHub or a BYO path. The documented report types include text outputs, PPTX files, PNG/SVG/PDF/TIFF figure assets, research evidence files, runnable web pages, screenshots, MP4 media, subtitles, transcripts and source code, depending on the comparison mode.

Known limits

Image-generation comparison is listed as planned rather than supported. For external GitHub candidates, the README recommends checking licence, dependencies and final output paths before execution. Simple deterministic tasks are explicitly outside the intended use case.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to forkprobe

mirage

strukto-ai

3.5k

Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in process; docker, e2b, daytona remote), and installed CLIs (git, gh, slack, linear, ntn, gws, or one you register) as head words in the virtual terminal.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceTypeScriptyesterday

AI review

mirage

What it is — mirage provides a unified virtual filesystem for AI agents, allowing bash tools to operate across mounted resources.

Who it is for — It is suitable for AI agents that use bash tools and need to access multiple backends such as S3 and Slack at the same time. It is not suitable for agents that only run on local filesystems without remote mounted services.

Watch out — No obvious issues found. There is a static check prompt indicating it will execute shell commands. Sandbox testing was not performed.

The verdict — I would not install it because sandbox testing was not performed.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

oh-dsh

hust-open-atom-club

239

Community distribution: TUI, desktop, and Web UI as one bundle with layered installation.

Installed cleanly when we ran it

GitHub sourceTypeScriptyesterday

AI review

oh-dsh

What it is — DeepSeek Harness community distribution bundles TUI, desktop and Web UIs.

Who it is for — Developers needing to use DeepSeek Harness for local AI agent coding with workspace capabilities should install it. Users only relying on cloud model services without local tools can skip this.

Watch out — Source installation requires Node.js and build tools. Sandbox test passed, registered in new profile. No obvious issues found.

The verdict — I would install it because it unifies three interfaces for DeepSeek Harness local development, but the tradeoff is building from source.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
Details

plugin-registry

vlln

54

Ecosystem infrastructure: a thin browser console for managing official repository plugins (zero patches) plus a make-dsh-plugin skill for guided plugin development.

Installed cleanly when we ran it

GitHub sourceTypeScriptyesterday

AI review

plugin-registry

What it is — A thin browser console for managing DeepSeek Harness profile plugin installation states, plus a make-dsh-plugin skill for guided official plugin development.

Who it is for — When developing third-party DeepSeek Harness plugins or maintaining plugin lists inside profiles, this console displays installation states and supplies development guidelines. If you only run pre-built official plugins and never create new ones, you do not need to install it.

Watch out — It was successfully installed in a fresh profile and registered by Harness. No obvious issues were found, though the plugin-type comparison and gotchas section in the skill references should be reviewed before any development.

The verdict — I would install it for the development standards it supplies, but it is not essential if the only task is to run existing official plugins.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
Source

dsh-multica-runtime

forrestchang

46

Run the dsh runtime on Multica.

Installed cleanly when we ran it

GitHub sourceTypeScript4d ago

AI review

dsh-multica-runtime

What it is — Private runtime bridge between Multica and DeepSeek Harness.

Who it is for — Developers needing DSH runtime integration in the Multica environment. For developers using standard DSH environments, this bridge serves no purpose.

Watch out — Sandbox test passed: installed in a new profile and registered with harness. The plugin executes shell commands.

The verdict — I would install it because it requires no changes to DeepSeek Harness.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

dsh-plugin-check

omdsh-dev

24

Plugin health checks: manifest protocol / patch format / build traps, zero-dependency and read-only.

Installed cleanly when we ran it

GitHub sourceTypeScriptyesterday

AI review

dsh-plugin-check

What it is — This is a zero-dependency read-only DeepSeek Harness plugin health check tool that scans plugin repositories and outputs compliance reports on manifest protocols, patch formats and build traps.

Who it is for — When you maintain multiple DeepSeek Harness plugin repositories in your organization and need regular checks on manifest protocols, patch formats and build traps, this tool fits your use case. If you only run a single plugin or your repository has already passed manual review, you do not need this tool.

Watch out — Sandbox testing passed: installed in a fresh profile and registered into harness. Static checks may mention executing shell commands but do not execute them. No other obvious issues found.

The verdict — I would install it because it provides automated compliance checks that reduce integration pitfalls in organizational plugin workflows, but only if installed via the profile bundle method.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

dsh-user-experience

DietCokewithSugar

19

Finds potential UX issues in your project: automatically reviews React/TypeScript code, pinpoints each problem, and gives concrete suggestions.

Installed cleanly when we ran it

npm packageTypeScriptyesterday

AI review

dsh-user-experience

What it is — Scans React, TypeScript, JavaScript, and Vue 3 code to simulate user personas, detect UX issues, and provide concrete suggestions.

Who it is for — When developing a React application with DeepSeek Harness and needing UX simulation capabilities, this plugin is suitable. If your project uses Svelte or Vue 2 frameworks, you do not need to install this plugin, as it does not support analysis for those languages.

Watch out — Sandbox test passed successfully with installation and registration in a fresh profile and no obvious issues found. It can obtain browser evidence when rendered page support is available, but relies only on static evidence without browser environment.

The verdict — I would install it because it automatically runs the walkthrough after file edits and provides locatable UX optimization suggestions.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
Source