Back to directory

j-space-cognition-suite

Maintenance: Active

tiger3807861189/j-space-cognition-suite

J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.

View on GitHub
$ dsh plugin add j-space-cognition-suite

3,011

stars

222

forks

Python

Language

Apache-2.0

License

2026-07-22

Created

2026-09-14

Last push

Apache-2.0 Python Skill for selectively managed agent workspaces and optional `.jspace/` loop state. The README does not document DeepSeek Harness-native setup or rollback.

DSH integration

Ecosystem-related

Author-claimed

Safety audit

Unaudited

Last verified

2026-09-13

License

Apache-2.0

01What can it help you accomplish?

  • Organize multi-step agent work that needs deep reasoning, tool use, verification, and recovery.

    A selectively loaded workspace approach and an optional controller for durable loop state; model weights and training remain unchanged.

    People using an AI host with a native Skill loader, or a chat/API environment that can provide system or developer instructions and file or retrieval tools.

02How to install into DeepSeek Harness

Prerequisites

  • A user-level Skills directory used by the AI host.
  • An available Python 3 interpreter for the integrity check.

Installation steps

  1. 01

    Download or clone the repository.

  2. 02

    Copy the complete `j-space/` directory to the host's user-level Skills directory so the entry is `<skills-directory>/j-space/SKILL.md`.

  3. 03

    Reload the host when it discovers Skills at startup.

Verify the integration

  • Run `<python-command> <skills-directory>/j-space/scripts/verify_suite.py` with an available Python 3 interpreter.

03DSH integration and capability boundaries

DSH integrationEcosystem-related

Host-generic Skill and system/developer-instruction integration; the README does not document a DeepSeek Harness-specific connector or command.

  • Selective workspace loading

    A task and the relevant modules or references.One or two load-bearing ideas remain active while the rest is externalized and loaded on demand.

  • Optional loop-state controller

    Commands for the resolved Skill path while the task workspace is the current directory.Recorded and reported loop state, including a ledger, checkpoints, open questions, seam reports, ship checks, and resume information.

    Writes working state only under the task workspace's `.jspace/` directory.

04Who is it for? When not to use it?

Good for

  • People using an AI host with a native Skill loader, or a chat/API environment that can provide system or developer instructions and file or retrieval tools.

Not for

  • Keep the installed directory intact because the entry routes to relative paths under modules, references, and scripts.

05Compatibility, maintenance and safety notes

  • Keep the installed directory intact because the entry routes to relative paths under modules, references, and scripts.
  • Using the optional controller writes working state beneath `.jspace/` in the current task workspace.
2026-07-222026-09-02v3.7.4

Apache-2.0; README documents the V3.7 package.

06Frequently asked questions

Does the README provide a native DeepSeek Harness integration?

No DSH-specific connector or command is documented. The README instead describes a cross-platform Skill, direct installation for hosts with native Skill loaders, and a system/developer-instruction route for chat or API environments.

How should I install it for a DeepSeek Harness workflow?

Use the mechanism your host supports for Skills: copy the complete `j-space/` directory into its user-level Skills directory, preserving the expected `j-space/SKILL.md` entry. The README does not name a DeepSeek Harness directory.

How can I verify the installation?

The README supplies an integrity-check command: run `<python-command> <skills-directory>/j-space/scripts/verify_suite.py` with an available Python 3 interpreter.

What does the optional controller change in my DSH task workspace?

It records and reports loop state under `.jspace/` in the current task workspace. The README says solution choice remains with the model.

08Data and sources

  • Author-claimedgithub.com988d07b8b5e7…

    It is packaged as a Skill for cross-platform use, selective loading, and low-friction integration.

  • Author-claimedgithub.com988d07b8b5e7…

    An environment with a native Skill loader can install `j-space/` directly.

This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-13. Found an error? Submit a correction.

🏆

Best DeepSeek Harness Plugins

Twelve plugins worth installing first — picked from the whole catalog, across every category.

DSH Plugins is an independent community directory of DeepSeek Harness plugins. Not affiliated with or endorsed by DeepSeek. Third-party plugins are not security-audited — review the source before installing.

New DeepSeek Harness plugins, weekly. No spam.