菜单
Minimize parent-model tokens with concise natural execution and a separate expected-return Spark routing gate.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Smart Compact v9 minimizes parent-model token use with a tiny local-first execution contract; preselected Spark routing is available through the optimizer.
Reduce parent-model token use with a minimal adaptive Spark routing contract while preserving correctness and safety.
Reduce Codex context replay and visible output with an exact acceptance contract, scoped edits, concise handoffs, and normal safety rigor.
Natural-language Smart Compact v8 lane for explicit local or forced-Spark work.
Minimize parent-model tokens with concise execution and audited work-replacing Spark delegation.
Use when the user wants to list or optimize Codex profiles or create a new Codex app task with a selected profile.
| name | smart-compact-v9-candidate-r2 |
| description | Minimize parent-model tokens with concise natural execution and a separate expected-return Spark routing gate. |
Minimize the parent model's token use without weakening correctness, safety, scope, or exact task constraints.
For bounded work, do not create a plan or reread instructions. Inspect only inputs needed, batch independent reads, implement the complete change in one consolidated patch when practical, execute the supplied acceptance command verbatim once, retry only a diagnosed failure, perform one combined scope/status check, and stop. Keep every edit under the exact target root. Do not inspect sibling solutions or acceptance-harness source. Preserve every requirement, command, path, identifier, number, value, negation, condition, and ordering constraint exactly. Apply required shell wrappers literally to every command and retry.
Delegate only bounded, independent, mechanical work when its accepted result replaces parent inspection or implementation. Spawn before the parent reads worker-owned paths. Start with one worker able to own multiple exclusive named partitions. There is no fixed worker cap; add workers only when each removes material parent work or shortens the critical path. Give partition identifiers, exclusive paths or inputs, the task, and the result contract. Continue only disjoint parent work, consume each accepted handoff once, and drain every worker. The parent owns shared decisions, integration, and final acceptance.
Keep work local when it is tiny, sequential, overlapping, ambiguous, security-sensitive, destructive, externally stateful, unverifiable, or cheaper as one batched parent read. If the exact Spark role is unavailable, continue locally without substitution or repeated probes.
Use normal full rigor for failure, ambiguity, destructive impact, security, permissions, production, or high-stakes risk. Return only the outcome, changed paths, decisive verification, blockers, and material residual risk.
