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 |
references/problem-model.md
View on GitHub# J-Space Problem Model
Load this only when the task admits two plausible readings that would produce different
actions or deliverables, or when a stated constraint, permission, tool, or existing capability
would remain idle under the first fluent plan. A merely difficult task does not need it.
> I have a fluent plan; we need to know whether it solves the task that was actually given.
> Let's settle the problem model before we act.
## Name the model
Write five short inner lines:
1. **Commit** — what is fixed before any action: the goal, contract, constraints, and prior
decisions.
2. **Move** — what you may choose, call, change, or observe during the work.
3. **Hidden** — what remains unknown when that choice is made.
4. **World** — what the environment, user, tests, or adversary determines afterwards.
5. **Success** — the complete predicate, including alternatives, exceptions, and visible
effects.
These are a problem model, not a checklist for the user. Keep them in the inner or ledger
register.
## Test the reading
Ask one counterfactual question: **if I remove this stated clause, does my plan stay the
same?** If yes, the clause has been named but not used. A granted capability is used only when
it changes the strategy — when you call it, extend it, feed it, or deliberately choose not to
use it for a stated task-relevant reason.
Fork only when the text, repository, interface, or evidence supports a real alternative.
Do not manufacture interpretations for completeness. Compare the actions and deliverables
that follow from each reading, then retain the one supported by the task and its actual
contracts. If the evidence cannot decide and the choice would materially change the result,
hand that choice to the user.
## Keep verification independent
Evidence aimed inside one reading can test execution without testing whether that reading is
the right task. A candidate and reference that encode the same task model may agree perfectly
and still answer the wrong question. Settle the interpretation first; then use
`../modules/empirics.md` to test the weakest claim inside it.
In an evaluation or benchmark, hidden answers, graders, or isolation boundaries are not
empirical instruments. Ordinary fixtures and expected outputs may be legitimate project
contracts when the task authorizes their use; treat them according to that task rather than
as a universal prohibition.
## Return
Carry three things back to the calling route: the surviving reading, the clause that decided
it, and the full success condition. If the fork arose during verification, resume
`../modules/empirics.md` inside that reading; otherwise use `../modules/deep-reasoning.md` when
the task needs a reasoning chain. The fork is settled when each stated condition has a role,
not when the protocol has produced more prose.
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 |