Skip to content
Back to search

parallax

MarketplaceWorks with Claude CodeGitHub

A lightweight workflow plugin for hands-off AI coding with DeepSeek Harness, Claude Code, GitHub Copilot, and more.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ai4xe--parallax/badge.svg)](/listings/ai4xe--parallax)

HTML

<a href="/listings/ai4xe--parallax"><img src="/api/listings/ai4xe--parallax/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Code

- **Option 1: Installer** (recommended):

  git clone https://github.com/AI4XE/Parallax.git
  bash Parallax/install.sh /path/to/your-project

- **Option 2: Manual copy**: copy each folder from `platforms/claude-code/skills/` into `<your-project>/.claude/skills/`. - **Option 3: Claude Code plugin marketplace**: `/plugin marketplace add AI4XE/Parallax`, then `/plugin install parallax`. Slash commands get namespaced (`/parallax:qstart`); natural-language triggering (e.g. "qstart") still finds them.

**Note**: the team track starts an additional, separate headless executor process; the orchestrator manages and reclaims it.

> **Tip**: running Claude Code inside `tmux` together with a plugin is the most compatible setup; you can also use tools such as [cc-connect](https://github.com/chenhg5/cc-connect) to connect the session to a chat app for remote follow-up.

DeepSeek Harness

- **Option 1: Plugin from npm** (preferred — no copying, re-run to upgrade): In the DSH web UI: **Plugins → Add plugin → enter `parallax-dsh`** (the plugin list can take ~30 s to load; choose the npm registry), install it, toggle the plugin **on**, then restart the profile. Or from the CLI:

  dsh plugin --profile <profile> add parallax-dsh

Requires the Node runtime supplied by dsh and pnpm visible on the `dsh` process PATH (e.g. via corepack); restart the profile after installing. Remove with `dsh plugin --profile <profile> remove parallax-dsh`. **Zero extra setup**: the bundle registers the skills and the native handoff hook and applies `subagent.maxDepth: 3`; do not edit rules, profiles, patches or permission settings for handoff. - **Option 2: Build the bundle from this repository**:

  git clone https://github.com/AI4XE/Parallax.git
  node Parallax/platforms/deepseek-harness/bundle/build.mjs
  dsh plugin --profile <profile> add "file:<absolute path to Parallax>/platforms/deepseek-harness/bundle"

Windows can run both commands natively; quote paths containing spaces. The installed bundle behaves exactly like the npm install (full native handoff, zero extra setup).

Skills-only copying (`install.sh --platform deepseek-harness`) is **not a supported install**: it provides the skill text only, with no native handoff or team support.

**Note**: Parallax also runs under DeepSeek Harness's `workspace-write` permissions.

Then, in a DSH session with your project as the working directory, just say: `qstart` (or `wish` / `Parallax`).

Copilot

- **Option 1: Marketplace** (recommended): search **Parallax for Copilot** in the VS Code Marketplace (publisher `ai4e`) and install it. - **Option 2: Project install** via installer:

  git clone https://github.com/AI4XE/Parallax.git
  bash Parallax/install.sh --platform copilot /path/to/your-project

- **Option 3: Manual copy**: copy `platforms/copilot/{skills,agents,instructions}` into `.github/`. Do not overwrite an existing `copilot-instructions.md` — merge it.

**Note**:

1. On first run, run **Developer: Reload Window** once (skills and agents are discovered on reload). 2. Recommended: set the chat permission mode to **Allow all** (or Autopilot) — setting key `chat.defaultConfiguration` — so cross-session hand-off and subagent reviews run without approval prompts. The default Manual mode also works; you approve each tool type once per session.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines
  1. {
  2. "name": "parallax",
  3. "owner": {
  4. "name": "AI4XE"
  5. },
  6. "plugins": [
  7. {
  8. "name": "parallax",
  9. "version": "2.0.1",
  10. "description": "Wish-driven development loop for Claude Code (qstart / qgo / bcheck / gclear / rcheck / xwrap / wish).",
  11. "source": "./",
  12. "skills": "./platforms/claude-code/skills"
  13. }
  14. ]
  15. }
README.md · README · 158 lines
  1. ![Parallax](assets/banner.svg)
  2. Parallax is a lightweight workflow plugin for hands-off AI coding, on top of your agent harness.
  3. Just say what you want, make a few choices, hand it off — an agent team takes it from there. You own the goal; the agents own the work, independent audits, and context management.
  4. [中文文档](README.zh-CN.md)
  5. [![Claude Code](https://img.shields.io/badge/Claude_Code-Install-6B4FBB?logo=anthropic&logoColor=white)](#claude-code)
  6. [![DeepSeek Harness](https://img.shields.io/badge/DeepSeek_Harness-Install-4D6BFE?logo=deepseek&logoColor=white)](#deepseek-harness)
  7. [![VS Code Copilot](https://img.shields.io/badge/VS_Code_Copilot-Install-0098FF?logo=githubcopilot&logoColor=white)](https://marketplace.visualstudio.com/items?itemName=ai4e.parallax-github-copilot)
  8. [![Listed on dsh-plugin.org](https://dsh-plugin.org/badges/listed.svg)](https://dsh-plugin.org/plugins/ai4xe/parallax)
  9. [![License](https://img.shields.io/github/license/AI4XE/Parallax)](LICENSE)
  10. [![GitHub stars](https://img.shields.io/github/stars/AI4XE/Parallax)](https://github.com/AI4XE/Parallax)
  11. ## Three steps
  12. > **Plugin trigger words**: `wish` · `Parallax` · `qstart`
  13. 1. **Wish** — say what you would like, as casually as you like. You do not need to have it figured out; add more in several messages and say "that's all" when you are done.
  14. 2. **Choose** — the agent researches first, then aligns with you one question at a time; you just pick, or add requirements and keep discussing as you go.
  15. 3. **Hand off** — the agent team takes it from there: plan → independent review → new-session execution → independent audit → scoped commit → wrap-up.
  16. > **Two modes**
  17. > - **solo** (default): you work directly with the execution session; the current session is the executor. Suited to everyday use.
  18. > - **team**: your conversation always stays with the orchestrator while the executor runs in its own session. Suited to large and very long tasks.
  19. > **Automatic context management**
  20. > - **At task start**: once the plan passes review, execution continues in a new session.
  21. > - **Long-running tasks** (team tier): context is handed off automatically at about 60%, keeping the AI clear-headed with no interruption to the task.
  22. https://github.com/user-attachments/assets/c85a9a89-2afa-44b0-a4f5-bf6db1db3001
  23. ## Platform support
  24. - **Claude Code** — Linux ✓ · Windows (WSL) ✓ · macOS ?
  25. - **DeepSeek Harness** — Linux ✓ · Windows ✓ · macOS ?
  26. - **GitHub Copilot (VS Code)** — Windows ✓ · Linux ? · macOS ?. **Currently solo only.**
  27. `?` means the code is written for compatibility and portability, but has not been actually tested; please open an issue with what you see.
  28. ## Install
  29. ### Claude Code
  30. - **Option 1: Installer** (recommended):
  31. ```bash
  32. git clone https://github.com/AI4XE/Parallax.git
  33. bash Parallax/install.sh /path/to/your-project
  34. ```
  35. - **Option 2: Manual copy**: copy each folder from `platforms/claude-code/skills/` into `<your-project>/.claude/skills/`.
  36. - **Option 3: Claude Code plugin marketplace**: `/plugin marketplace add AI4XE/Parallax`, then `/plugin install parallax`. Slash commands get namespaced (`/parallax:qstart`); natural-language triggering (e.g. "qstart") still finds them.
  37. **Note**: the team track starts an additional, separate headless executor process; the orchestrator manages and reclaims it.
  38. > **Tip**: running Claude Code inside `tmux` together with a plugin is the most compatible setup; you can also use tools such as [cc-connect](https://github.com/chenhg5/cc-connect) to connect the session to a chat app for remote follow-up.
  39. ### DeepSeek Harness
  40. - **Option 1: Plugin from npm** (preferred — no copying, re-run to upgrade):
  41. In the DSH web UI: **Plugins → Add plugin → enter `parallax-dsh`** (the plugin list can take ~30 s to load; choose the npm registry), install it, toggle the plugin **on**, then restart the profile. Or from the CLI:
  42. ```bash
  43. dsh plugin --profile <profile> add parallax-dsh
  44. ```
  45. Requires the Node runtime supplied by dsh and pnpm visible on the `dsh` process PATH (e.g. via corepack); restart the profile after installing. Remove with `dsh plugin --profile <profile> remove parallax-dsh`. **Zero extra setup**: the bundle registers the skills and the native handoff hook and applies `subagent.maxDepth: 3`; do not edit rules, profiles, patches or permission settings for handoff.
  46. - **Option 2: Build the bundle from this repository**:
  47. ```bash
  48. git clone https://github.com/AI4XE/Parallax.git
  49. node Parallax/platforms/deepseek-harness/bundle/build.mjs
  50. dsh plugin --profile <profile> add "file:<absolute path to Parallax>/platforms/deepseek-harness/bundle"
  51. ```
  52. Windows can run both commands natively; quote paths containing spaces. The installed bundle behaves exactly like the npm install (full native handoff, zero extra setup).
  53. Skills-only copying (`install.sh --platform deepseek-harness`) is **not a supported install**: it provides the skill text only, with no native handoff or team support.
  54. **Note**: Parallax also runs under DeepSeek Harness's `workspace-write` permissions.
  55. Then, in a DSH session with your project as the working directory, just say: `qstart` (or `wish` / `Parallax`).
  56. ### Copilot
  57. - **Option 1: Marketplace** (recommended): search **Parallax for Copilot** in the VS Code Marketplace (publisher `ai4e`) and install it.
  58. - **Option 2: Project install** via installer:
  59. ```bash
  60. git clone https://github.com/AI4XE/Parallax.git
  61. bash Parallax/install.sh --platform copilot /path/to/your-project
  62. ```
  63. - **Option 3: Manual copy**: copy `platforms/copilot/{skills,agents,instructions}` into `.github/`. Do not overwrite an existing `copilot-instructions.md` — merge it.
  64. **Note**:
  65. 1. On first run, run **Developer: Reload Window** once (skills and agents are discovered on reload).
  66. 2. Recommended: set the chat permission mode to **Allow all** (or Autopilot) — setting key `chat.defaultConfiguration` — so cross-session hand-off and subagent reviews run without approval prompts. The default Manual mode also works; you approve each tool type once per session.
  67. ## Skills
  68. Parallax turns "please build this" into a self-advancing, self-reviewing loop:
  69. | Skill | Role |
  70. |---|---|
  71. | **qstart** | Discussion entry: requirements → research → one-question-at-a-time alignment → complete overview. |
  72. | **qgo** | Hand-off: re-checks the discussion, writes the plan, passes the **bcheck** gate (score ≥ 4/5), then a clean-context agent executes autonomously → **rcheck** audit → scoped commit. |
  73. | **bcheck** | Independent adversarial review of the plan *before* execution. The doer never grades their own homework. |
  74. | **gclear** | Saves a distilled brief and hands it to clean model context, with delivery verification; the platform adapter supplies the native mechanism. |
  75. | **rcheck** | Independent reconciliation audit *after* execution: every "done" claim is verified against reality. |
  76. | **xwrap** | Wrap-up: obvious-problem report, todo update, wrapup doc, smart scoped git commit. |
  77. | **wish** | One-line wish entry (许愿创造 / 许愿编程) that forwards to **qstart**. |
  78. One line: **qstart** (align the wish) → **qgo** (release; plan gated by bcheck → clean-context execution → rcheck audit → commit) → **xwrap** (wrap up).
  79. Two collaboration modes: planning and execution live in different sessions and hand off automatically; **solo** has no orchestrator and the execution session carries the work to the end; in **team**, the execution stage is run jointly by the orchestrator and an independent executor. `ver` / `nover` select versioned vs non-versioned tasks.
  80. How the hand-off works on each harness:
  81. - **Claude Code**: `gclear` drives `/clear` and verifies the injection against the session transcript; the team track runs a headless stream-json executor in its own process, started and watched by the bundled driver. The CLI `tmux` requirement below still applies to `gclear`'s detached launcher.
  82. - **DeepSeek Harness**: the full bundle provides `parallax_handoff`, which replaces model-visible history with a concise handoff at a native safe step. The SID, agent, append-only user transcript, Web tab/composer and child ownership stay intact, and work resumes automatically. In solo you keep talking directly to the executor; in team the original window stays the orchestrator and manages native child executors via `list_agents` / `send_message` / `interrupt_agent`. The bundle sets `subagent.maxDepth: 3`, so an executor can spawn its own independent reviewers.
  83. ## Tested versions
  84. - Claude Code **2.1.322**, **2.1.140**
  85. - DeepSeek Harness (dsh) **0.2.2-rc.1**
  86. - VS Code **1.146.0** with bundled GitHub Copilot Chat **0.74.0**
  87. ## Philosophy
  88. - **The harness is a key part.** Real quality comes from agent collaboration under harness constraints — not from a magic prompt.
  89. - **Three steps, one hand-off.** Wish → choose → hand off. You own the goal and the boundaries; the agents execute, manage context, and independently verify and cross-review, so you steer instead of supervising every step.
  90. - **The loop.** Input → analysis → plan → execution → acceptance → delivery. Every step gets independent review, scoring, and iteration — the one doing the work and the one checking are different entities with isolated contexts.
  91. - **Three pillars**: phase isolation (strategy vs tactics) · adversarial acceptance (anti-sycophancy: the reviewer's job is to break it) · TDD (see it fail before you see it pass).
  92. > **Name**: from Greek *parallaxis* — para- "beside" + allassein "to change". Viewed from beside, the position shifts: change the viewpoint and what you see changes. Self-review from inside cannot; an outside look can.
  93. ## Compatibility
  94. - **Git**: recommended — the workflow uses Git roots, scoped commits, and hand-off checkpoints; `qstart` runs one cheap `git --version` during research and asks once whether to install it if missing (it does not block).
  95. - **Claude Code**: Linux · macOS · Windows WSL. Bash 4+, Python ≥ 3.11 (stdlib only; no third-party packages), `tmux` for the CLI hand-off launcher.
  96. - **DeepSeek Harness**: **Runtime uses only dsh's Node and injected native services** — no Python, Bash, zstd CLI, tmux or patched harness.
  97. - **GitHub Copilot**: pure Markdown skills, zero runtime dependencies. Solo only.
  98. ## Configuration
  99. Everything works with zero configuration. Optional knobs, each a tiny local file (kept across upgrades by the installer):
  100. - `skills/bcheck/skill.conf`, `skills/rcheck/skill.conf` — `review_model=` : model for the independent review subagent. Empty = session default (never up- or down-shifted).
  101. - Claude Code only: `skills/gclear/gclear.conf` — `MODEL_ALIASES=""` : space-separated `alias=full-id` pairs for `gclear --model`; plus timeout/retry tuning keys.
  102. - Default reply language per skill (trigger-message language and spoken requests override it): Claude Code reads the `display_lang` frontmatter key; DeepSeek Harness reads `metadata.display_lang`.
  103. ## Upgrading
  104. Re-run the installer (`bash install.sh [--platform <p>] <project>`) — it swaps skills atomically and keeps your local `*.conf` files. Claude Code plugin installs: `/plugin update parallax`. DeepSeek Harness bundle installs: re-run `node platforms/deepseek-harness/bundle/build.mjs`, then `dsh plugin --profile <profile> add "file:<bundle path>"` and restart that profile. Each skill versions itself in its `SKILL.md` frontmatter.
  105. ## Contact
  106. Questions or feedback: open an issue or email [MatClaw@agentmail.to](mailto:MatClaw@agentmail.to).
  107. ---
  108. MIT — see [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.