An Apache-2.0 inference-time cognitive-control Skill for DeepSeek Harness and other agents: nine modules plus references and an optional task-state controller, loaded by copying `j-space/` into the host Skills directory.
DSH integration
Compatible
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-23
License
Apache-2.0
01What can it help you accomplish?
Add inference-time cognitive control to DeepSeek Harness (or any supported host) for deep reasoning, long-horizon work, tool use, verification and recovery
A selectively loaded Skill (one entry + nine modules + four references + an optional standard-library controller for durable task state)
DeepSeek Harness (dsh) and other coding-agent users who want model-agnostic inference-time control without changing model weights
02How to install into DeepSeek Harness
Prerequisites
- Python 3 interpreter available on the host (commonly `python`, `python3`, or `py -3`) for the integrity check
- A supported AI host's user-level Skills directory (the suite is packaged as a Skill for cross-platform use)
Installation steps
- 01
Download or clone this repository
- 02
Locate the user-level Skills directory used by your AI host
- 03
Copy the complete `j-space/` directory into it so the installed entry is `<skills-directory>/j-space/SKILL.md`
- 04
Run the integrity check: `<python-command> <skills-directory>/j-space/scripts/verify_suite.py`
- 05
Reload the host if it discovers Skills at startup
Verify the integration
- Run `<python-command> <skills-directory>/j-space/scripts/verify_suite.py` to run the integrity check
03DSH integration and capability boundaries
Packaged as a Skill for cross-platform use; copies into the host AI's user-level Skills directory so DeepSeek Harness can load it
Inference-time control system
agent's accessible working representations→managed workspace operating through one entry, nine selectively loaded modules, four supporting references, and an optional standard-library controller
operates at inference time; model weights and training remain unchanged
04Who is it for? When not to use it?
Good for
- DeepSeek Harness (dsh) and other coding-agent users who want model-agnostic inference-time control without changing model weights
Not for
- The `j-space/` directory must remain intact because `SKILL.md` routes to relative paths under `modules/`, `references/`, and `scripts/`; the repository-level LICENSE and THIRD_PARTY_NOTICES.md must be redistributed when the package is shared standalone.
05Compatibility, maintenance and safety notes
- The `j-space/` directory must remain intact because `SKILL.md` routes to relative paths under `modules/`, `references/`, and `scripts/`; the repository-level LICENSE and THIRD_PARTY_NOTICES.md must be redistributed when the package is shared standalone.
Apache-2.0 · actively maintained (latest release v3.7.0, 2026-08-23)
06Frequently asked questions
How do I install J-Space Cognition Suite on DeepSeek Harness?
Copy the complete `j-space/` directory into your AI host's user-level Skills directory so the entry becomes `<skills-directory>/j-space/SKILL.md`, run `verify_suite.py` with a Python 3 interpreter, then reload the host.
Does J-Space change my model weights?
No. J-Space operates purely at inference time; model weights and training remain unchanged. It manages the agent's working representations into a controlled workspace.
How do I verify the install worked?
Run `<python-command> <skills-directory>/j-space/scripts/verify_suite.py` with your Python 3 interpreter. The directory must stay intact because SKILL.md routes to relative paths under modules/, references/, and scripts/.
Can I ask an AI agent to install it for me?
Yes. The README provides a ready prompt to paste into an agent that can access files and this repository; the agent performs the copy and integrity check on your behalf.
What happens if I redistribute the suite?
Include copies of both the repository-level LICENSE and THIRD_PARTY_NOTICES.md when redistributing `j-space/` as a standalone package.
07Related DSH workflows
dsh-web
by zhu1090093659
DeepSeek Harness (DSH) Web Plugin Aggregation Ecosystem · Everything is a plugin, distributed via the Creative Workshop
petdex
by crafter-station
A public gallery of animated pets for Codex, Claude Code, DeepSeek Harness, Hermes, OpenCode, Gemini CLI, and more.
deepseek-balance-whale-widget
by meteornox
Floating cartoon whale widget living in the DSH Web UI corner that auto-loads, refreshes DeepSeek balance every 60s (click to refresh), with drag/snap, left-flip mirror, squish animation, size scaling and rolling-number animation
dsh-deep-whale
by small-tailqwq
DSH Web GUI 鲸鱼娘主题皮肤（深海女仆工坊 maid-atelier：亮/暗双模式）
08Data and sources
It is packaged as a Skill for cross-platform use, selective loading, and low-friction integration.
/j-space/SKILL.md`. 4. Run the integrity check with an available Python 3 interpreter: ```text <python-command> <skills-…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-23. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.