Tiger3807861189/J-Space-Cognition-Suite / j-space
j-space
VerifiedOperate 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.7 KB |
| modules/broadcast.md | markdown | 9.8 KB |
| modules/capacity.md | markdown | 14.0 KB |
| modules/cyber.md | markdown | 8.6 KB |
| modules/deep-reasoning.md | markdown | 11.7 KB |
| modules/directed-focus.md | markdown | 9.3 KB |
| modules/empirics.md | markdown | 10.2 KB |
| modules/epistemics.md | markdown | 6.1 KB |
| modules/introspection.md | markdown | 9.8 KB |
| modules/markers.md | markdown | 12.8 KB |
| modules/orchestration.md | markdown | 8.4 KB |
| modules/repository.md | markdown | 7.8 KB |
| modules/self-monitoring.md | markdown | 14.9 KB |
| modules/shorthand.md | markdown | 14.3 KB |
| references/controller.md | markdown | 22.2 KB |
| references/engineering-evidence.md | markdown | 8.4 KB |
| references/exemplars.md | markdown | 18.5 KB |
| references/host-integration.md | markdown | 5.9 KB |
| references/induction-playbook.md | markdown | 21.5 KB |
| references/j-space-science.md | markdown | 36.5 KB |
| references/problem-model.md | markdown | 2.8 KB |
| scripts/control.py | script | 49.2 KB |
| scripts/host_bridge.py | script | 3.2 KB |
| scripts/jspace.py | script | 35.9 KB |
| scripts/verify_suite.py | script | 12.3 KB |
| scripts/workspace-ledger.md | markdown | 4.0 KB |
scripts/workspace-ledger.md
View on GitHub# J-Space Workspace Ledger — template
Use this standalone lightweight ledger for a bounded task or a conversation-only fallback.
For high and xhigh execution with Python and storage, use the shared structured state in
[the controller contract](../references/controller.md); do not create a competing ledger.
Copy the blank shell below to `.jspace/WORKSPACE.md`, then fill `Goal` and `Next` before the
first seam. Or let
`jspace.py note --goal "..." --next "..."` create it. If there is no filesystem here, keep the
five sections in the conversation and restate them at each seam — the file was never the point,
the re-reading was.
Five lines. Short enough to re-read in seconds, or it will not get re-read.
The optional `jspace.py note --check --by` uses a lexical heuristic, not semantic evidence
validation. `--by` must match both `VERIFIER` and `COVERAGE` in [jspace.py](jspace.py).
Recognized verifier families include tests, inspection, review, reproduction, comparison,
execution, measurement, logs, and assertions; coverage includes all/each, cases, inputs,
files, modules, sections, platforms, boundaries, samples, or an explicit sample count.
Both expressions also contain Chinese equivalents; the expressions are the exact supported
vocabulary. For example, use `reproduction of the reported case` or `manual inspection of
each changed section`. A bare `fixture` is not a recognized verifier. This advisory command
does not share the structured controller's free-form `--by` contract.
`jspace.py ship FILE` and `ship -` accept at most 8 MiB of encoded text, including any BOM.
Larger input returns exit 2 without auditing a truncated prefix. Split large outgoing text
into bounded artifacts. This advisory check does not establish correctness of binary or
multi-gigabyte deliverables; use their actual format validators and controller evidence.
```markdown
# J-Space Workspace Ledger
## Goal
## Core
## Verified
## Open
## Next
```
Write one testable completion condition under `Goal` and one immediate action under `Next`.
Add at most two live `Core` entries as `name — defining fact`; let the controller number
`Verified` and `Open` entries so their identifiers remain stable.
## The four rules that make it work
1. **Re-read at every seam.** This is the whole mechanism. Attention reaches any earlier token
equally, but only while that token is still in front of you.
2. **Preserve the record.** `Verified` is numbered and append-only. `Goal` and `Next` update;
an existing live `Core` slot changes only by an explicit swap; an `Open` entry closes against
a recorded checkpoint, which retains `closes: ?NN`; its number is never reused. When the
ledger is restated by hand, carry each `closes: ?NN` suffix with its row — a number's
retirement is recorded only there.
3. **`Next` is never empty.** A ledger with no next action is a ledger you have stopped using.
4. **Two live core entries.** More than two is not a hub, it is a list. The rest stay written
down and get reloaded per section.
## What does not belong here
Not the reasoning. Not the draft. Not a log of what you did.
The ledger holds *state* — what is settled, what is open, what is next. If a line would never be
read again, it belongs on the inner register or nowhere.
**It is also not a task list.** If your environment already tracks work items, keep using it —
that tracks *what is left to do*. The ledger tracks *what is now known*: the verified results
later steps are allowed to rely on, and the questions that are still open. They answer different
questions and neither replaces the other.
## Housekeeping
`.jspace/` is working state, not part of the project. It belongs in `.gitignore`, and it should
not be committed unless someone asks for it:
```
echo ".jspace/" >> .gitignore
```
Preserve this state while the task is active. Deleting it loses the supported checkpoints
and open questions needed to resume. Archive or remove task state only when that action is
within the user's scope; do not erase an incomplete record to bypass a control check.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |