- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add amplifthq/openmeld --skill verify-remote-agent-execution -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add amplifthq/openmeld --skill verify-remote-agent-execution -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add amplifthq/openmeld --skill verify-remote-agent-execution -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add amplifthq/openmeld --skill verify-remote-agent-execution -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/amplifthq/openmeld/tree/HEAD/.agents/skills/verify-remote-agent-execution來自發布者
A stop that wins before a reply is stored never becomes a completed reply, and a reply that is already stored stays a reply. Harm: the Space shows a successful answer after the member stopped the hosted agent, or a stop erases an answer that already landed.
The steps are compare-and-set transitions on one submission, so the spec is TLA+ and the checker is TLC 1.7.4 (jar sha256 936a262061c914694dfd669a543be24573c45d5aa0ff20a8b96b23d01e050e88). The code check calls the real functions with the in-memory storage from services/remote-agent/tests/storage.ts and rereads the terminal outcome using resolveRemoteAgentTerminalExecutionOutcome. Java 11 or newer must be on PATH. The check downloads the jar into ~/.cache/openmeld-tlc/ on first run.
Run it when a change touches any of these in services/remote-agent/agent-core/execution-state.ts:
initializeRemoteAgentExecutionStatemarkRemoteAgentExecutionProgressrequestRemoteAgentExecutionCancellationcompleteRemoteAgentExecutionStateresolveSettledExecutionStatusConfirmed against commit 965d9eb3219fa2c35789f9ab9a2206ab8699de9b. Move that commit forward only after you have confirmed that RemoteAgentExecution.tla and check.test.ts still describe those functions.
From the repository root, after pnpm install:
node .agents/skills/verify-remote-agent-execution/check.mjs
The stop-then-complete replay must return aborted. The persisted outcome must also be readable as aborted with no completed answer text. A failure during readback catches an inconsistent stored record even if completion returned the expected status.
Read every TLC result with /statechart. The user-facing labels are in view.mjs next to the spec.
settles a stop as stopped expected aborted and got completed: resolveSettledExecutionStatus no longer turns cancellation_requested into aborted. That is the bug the rule exists to catch.keeps a stored reply failed: stop after completed changed the row or reported it as stoppable.does not start after a stop that arrived first failed: initialization ignored the admission stop intent.AStopIsNotAReplyOrMoreWork to make TLC pass.One submission. repairRemoteAgentCompletedExecutionWithoutAnswer is not in the model: a completed row with no stored answer can still become failed. The chart hides the idle end step and a progress tick that stays on Working.
Use /maintain-formal-verification-skill to bring this check back in line.
Check Remote Agent native execution. A stop is not stored as a reply, and a stored reply is not rewritten as a stop. Use when changing initializeRemoteAgentExecutionState, markRemoteAgentExecutionProg
---name: verify-remote-agent-executiondescription: Check Remote Agent native execution. A stop is not stored as a reply, and a stored reply is not rewritten as a…---# .agents/skills/verify-remote-agent-execution/SKILL.md總覽
Check Remote Agent native execution. A stop is not stored as a reply, and a stored reply is not rewritten as a stop. Use when changing initializeRemoteAgentExecutionState, markRemoteAgentExecutionProgress, requestRemoteAgentExecutionCancellation, or completeRemoteAgentExecutionState.
常見問題
從發布者下載 .agents/skills/verify-remote-agent-execution/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/amplifthq/openmeld。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。