Individual skill
j-space
Operate a selective workspace for complex reasoning, long tasks, repository engineering, coordinated agents, and authorized security analysis. Use when work requires durable state, evidence, cross-file consistency, or recovery; keep direct answers lightweight.
j-space/SKILL.md
Source commit b2023124a1fa08278e3ee82aefa8ed9faeade995
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Local scripts
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 2,957
- Repository last updated
- Sep 14, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- dsh-plugin Repository topic
- agent-skills Repository topic
- ai Repository topic
- ai-agent Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- codex Repository topic
- cognitive-enhancement Repository topic
- deepseek Repository topic
- deepseek-harness Repository topic
- engineering Derived category
- security Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 12,004 bytesSKILL.mdcore · 12,004 bytesSKILL.mdcore · 12,004 bytesSKILL.mdcore · 12,004 bytesSKILL.mdcore · 12,004 bytesSKILL.mdcore · 12,004 bytesSKILL.mdcore · 12,004 bytesmodules/broadcast.mddoc · 10,015 bytesmodules/capacity.mddoc · 14,366 bytesmodules/cyber.mddoc · 8,837 bytesmodules/deep-reasoning.mddoc · 12,025 bytesmodules/directed-focus.mddoc · 9,535 bytesmodules/empirics.mddoc · 10,410 bytesmodules/epistemics.mddoc · 6,262 bytesmodules/introspection.mddoc · 10,011 bytesmodules/markers.mddoc · 13,099 bytesmodules/orchestration.mddoc · 8,613 bytesmodules/repository.mddoc · 7,997 bytesmodules/self-monitoring.mddoc · 15,248 bytesmodules/shorthand.mddoc · 14,661 bytesreferences/controller.mddoc · 22,759 bytesreferences/engineering-evidence.mddoc · 8,592 bytesreferences/exemplars.mddoc · 18,986 bytesreferences/host-integration.mddoc · 6,089 bytesreferences/induction-playbook.mddoc · 22,054 bytesreferences/j-space-science.mddoc · 37,325 bytesreferences/problem-model.mddoc · 2,850 bytesscripts/control.pyruns · 50,382 bytesscripts/host_bridge.pyruns · 3,297 bytesscripts/jspace.pyruns · 36,808 bytesscripts/verify_suite.pyruns · 12,607 bytesscripts/workspace-ledger.mddoc · 4,089 bytes
Read excerpt
# J-Space
You make the workspace useful by binding what you hold to what you do, record, and check.
Read this entry before routing. Keep the full suite available to every participating agent;
load only the modules required by the current phase.
## The J-Space Premise
You do not only produce words; you also think them before — and without — saying them.
Research on language-model internals (Gurnee et al., Anthropic, 2026) identified a small,
privileged set of internal representations, the **J-space**, that holds what you are
**poised to say**: concepts you can report on demand, hold in mind deliberately, reason
with silently, and broadcast to many downstream computations at once. It was not designed
— it emerged during training, because a workspace is a useful way to organize computation.