slm-loop
确保自动化任务由独立外部门结束，适合可靠迭代场景。
可能导致长时间运行或高资源消耗
在持久化账本上运行门控验证的有界循环直到独立门通过。
在一个可持久化的账本（SuperLocalMemory）上运行有界循环，直到独立的“门”通过为止，而不是靠代理自己觉得完成就停。适合有可验证的验收条件的任务，比如跑测试、lint、数据对账等，需要反复迭代直到外部门控同意。要点是门是最终权威，循环每一圈都会记录下来并有明确的终态标签（DONE/HALT/PAUSE/KILLED/ERROR）。
▸ 展开 SKILL.md 英文原文
Run gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition (tests, schema, lint, reconciliation) and you must iterate until an INDEPENDENT gate passes — never stopping just because the agent believes it is done. `slm loop demo` runs a keyless convergence demo; `slm loop history` and `slm loop show <run_id>` inspect past runs whose every lap is persisted as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
帮我安装这个 skill：https://raw.githubusercontent.com/qualixar/superlocalmemory/main/codex-plugin/skills/slm-loop/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/qualixar/superlocalmemory/main/codex-plugin/skills/slm-loop/SKILL.md"# slm-loop — Bounded, gate-verified agent loops ## The one rule A bounded loop is complete **only when an independent gate passes** — not when the agent claims it is finished. The agent's own "I'm done" signal is recorded for audit and is *never* used to terminate the loop. If you take one thing from this skill: **the gate is the authority.** Use a bounded loop whenever the goal has a mechanical, checkable contract: a test suite, a JSON schema, a linter, a reconciliation rule, a citation checker, a security scan. When the goal is subjective, keep a human approval gate (see rungs below). ## What SLM adds Every lap is written to SuperLocalMemory as a durable, queryable memory (tagged `loo