cybernetic-goals

Use when a formed task needs durable human-approved meaning, completion obligations, evidence claims, non-goals, or live/destructive authority boundaries.

Use when maintaining or resuming an existing v1 requirements.control.json run; new runs use forming-cybernetic-commitments.

Use when an existing v1 run must compile its reviewed control chain into runtime.control.json.

Use when optional local workflow guidance or legacy v1 workflow compatibility needs diagnosis.

Use when an existing v1 control chain requires design.control.json; v2 strategies remain agent-owned.

Use when cybernetic routing is requested but user input is pre-task intent or role-ambiguous context: confusion, dissatisfaction, risk sense, observed symptoms, failed attempts, method preference, process distrust, source material, declared current state, or unclear requested transformation.

Use when resuming an existing v1 run that already requires pre-goal control-chain compilation.

Use when an existing v1 requirements/design/goal/plan chain needs compatibility review.

Use when a formed task needs a decision between ordinary direct work and a durable commitment-controlled run.

Use when resuming an existing v1 bounded_runtime goal with goal.control.json and runtime.control.json.

Use when executing a v2 cybernetic run whose only approved task authority is commitment.control.json.

Use when executing an existing v1 compiled run.control.json/runtime.control.json chain.

Use when an existing v1 control chain requires plan.control.json execution policy artifacts.

Use when an existing v1 chain requires goal.control.json or bounded runtime compatibility.

Use when an approved non-trivial cybernetic requirements, design, and goal chain must be converted into an executable plan.control.json strategy before review.

Use when cybernetic requirements or solution design has a genuinely open search space and needs candidate paths, trade-offs, and discriminating questions before commitment.

Use when a cybernetic pre-goal or runtime failure is unclear, repeated, cross-component, or at risk of being patched without locating the failing invariant and owner.

Use when a compiled cybernetic runtime goal must execute the approved generation without redefining its requirements, plan, evidence rules, or completion claim.

Use when an approved cybernetic execution policy selects Parallel subagent-driven work with parallel-max-safe mode, explicit independence, locks, barriers, and human approval.

Use when an approved cybernetic execution policy selects Serial subagent-driven work, serial-single-active mode, and one active bounded implementer at a time.

Use when a cybernetic runtime is preparing any fixed, passing, deployed, accepted, or goal-achieved claim and must bind fresh evidence to the exact approved candidate.

Use when older prompts invoke cybernetic clarification terminology; prefer analyzing-cybernetic-requirements for formed task requirements analysis.

Use when a cybernetic skill invocation, artifact creation, blocked state, human feedback, or runtime outcome should be recorded as local metadata-only process evidence. Not for upload, skill self-modification, release, rollout, or accepting cloud candidates.