Skip to main content
A

parallax

ai4xe/parallax

A hands-off development plugin for AI coding agents (Claude Code, DeepSeek Harness, GitHub Copilot and more)

Install

dsh plugin --profile web add github:ai4xe/parallax

README

Parallax

Parallax is a lightweight enhancement layer on top of your coding-agent harness. You own the goal; the agents own the work, context management, and independent acceptance.

Install Parallax, then just wish it. Make it real. Say what you want, make a few choices, hand it off — an agent team does the work under independent review and in a clean session, audits the result, and commits it clean.

中文文档

Claude Code DeepSeek Harness VS Code Copilot License GitHub stars

Three steps

Plugin trigger words: wish · Parallax · qstart

  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.
  2. Choose — the agent researches first, then aligns with you one question at a time; you just pick.
  3. Hand off — the agent team takes it from there: plan → independent review → new-session execution → independent audit → scoped commit → wrap-up.

Two modes

  • solo (default): you work directly with the execution session; the current session is the executor. Suited to everyday use.
  • team: your conversation always stays with the orchestrator while the executor runs in its own session. Suited to large and very long tasks.

Automatic context management

  • At task start: once the plan passes review, execution continues in a new session.
  • Long-running tasks (team tier): context is handed off automatically at about 60%, keeping the AI clear-headed with no interruption to the task.

https://github.com/user-attachments/assets/c85a9a89-2afa-44b0-a4f5-bf6db1db3001

Platform support

  • Claude Code — Linux ✓ · Windows (WSL) ✓ · macOS ?
  • DeepSeek Harness — Linux ✓ · Windows ✓ · macOS ?
  • GitHub Copilot (VS Code) — Windows ✓ · Linux ? · macOS ?. Currently solo only.

? means the code is written for compatibility and portability, but has not been actually tested; please open an issue with what you see.

Install

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 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.

Skills

Parallax turns "please build this" into a self-advancing, self-reviewing loop:

SkillRole
qstartDiscussion entry: requirements → research → one-question-at-a-time alignment → complete overview.
qgoHand-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.
bcheckIndependent adversarial review of the plan before execution. The doer never grades their own homework.
gclearSaves a distilled brief and hands it to clean model context, with delivery verification; the platform adapter supplies the native mechanism.
rcheckIndependent reconciliation audit after execution: every "done" claim is verified against reality.
xwrapWrap-up: obvious-problem report, todo update, wrapup doc, smart scoped git commit.
wishOne-line wish entry (许愿创造 / 许愿编程) that forwards to qstart.

One line: qstart (align the wish) → qgo (release; plan gated by bcheck → clean-context execution → rcheck audit → commit) → xwrap (wrap up).

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.

How the hand-off works on each harness:

  • 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.
  • 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.

Tested versions

  • Claude Code 2.1.322, 2.1.140
  • DeepSeek Harness (dsh) 0.2.2-rc.1
  • VS Code 1.146.0 with bundled GitHub Copilot Chat 0.74.0

Philosophy

  • The harness is a key part. Real quality comes from agent collaboration under harness constraints — not from a magic prompt.
  • 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.
  • 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.
  • 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).

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.

Compatibility

  • 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).
  • Claude Code: Linux · macOS · Windows WSL. Bash 4+, Python ≥ 3.11 (stdlib only; no third-party packages), tmux for the CLI hand-off launcher.
  • DeepSeek Harness: Runtime uses only dsh's Node and injected native services — no Python, Bash, zstd CLI, tmux or patched harness.
  • GitHub Copilot: pure Markdown skills, zero runtime dependencies. Solo only.

Configuration

Everything works with zero configuration. Optional knobs, each a tiny local file (kept across upgrades by the installer):

  • skills/bcheck/skill.conf, skills/rcheck/skill.conf — review_model= : model for the independent review subagent. Empty = session default (never up- or down-shifted).
  • Claude Code only: skills/gclear/gclear.conf — MODEL_ALIASES="" : space-separated alias=full-id pairs for gclear --model; plus timeout/retry tuning keys.
  • 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.

Upgrading

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.

Contact

Questions or feedback: open an issue or email MatClaw@agentmail.to.


MIT — see LICENSE.

Related plugins