agent-integration
Attach ControlKeel to agents, verify MCP connectivity, confirm native skills availability, and choose the right distribution target for each client.
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。
菜单
Attach ControlKeel to agents, verify MCP connectivity, confirm native skills availability, and choose the right distribution target for each client.
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
| name | agent-integration |
| description | Attach ControlKeel to agents, verify MCP connectivity, confirm native skills availability, and choose the right distribution target for each client. |
| when_to_use | Activate when setting up CK with a new agent, installing the plugin, configuring MCP, or when the user asks how to attach ControlKeel to their tool. |
| argument-hint | [agent name or tool to integrate] |
| license | Apache-2.0 |
| compatibility | ["codex","claude-standalone","claude-plugin","copilot-plugin","github-repo","open-standard","cline-native","cursor-native","windsurf-native","continue-native","letta-code-native","pi-native","roo-native","goose-native","opencode-native","gemini-cli-native","kiro-native","kilo-native","amp-native","augment-native","hermes-native","multica-native","openclaw-native","devin-terminal-native","warp-native","droid-bundle","forge-acp"] |
| disable-model-invocation | true |
| metadata | {"author":"controlkeel","version":"2.0","category":"integration"} |
Use this skill when the task is attaching or distributing ControlKeel across agents.
.mcp.json, CLAUDE.md, and .claude/commands.ck_attach, validate the canonical project inside CK_PROJECT_ROOT for every scope. User scope changes native destinations but does not authorize another project; consult the target matrix for hosts whose MCP registration also updates a user-managed config path.controlkeel setup, controlkeel attach <host>, controlkeel attach doctor, controlkeel provider doctor, controlkeel status, and controlkeel findings.Cursor’s Settings → Rules, Skills, Subagents (and related Commands, Hooks, Plugins) align to repo files ControlKeel already generates on controlkeel attach cursor:
| Cursor concept | CK attach output | Notes |
|---|---|---|
| Rules | .cursor/rules/controlkeel.mdc | Always-on governance instructions for the agent. |
| Skills | .cursor/skills/* plus .agents/skills/* | Native Cursor skills tree plus open-standard AgentSkills for import tools. |
| Commands | .cursor/commands/*.md | Slash-style review / plan / annotate / last flows. |
| Agents / Subagents | .cursor/agents/*.md, .cursor/background-agents/*.md | Governor-style prompts and background workflow guidance; hooks include subagentStart. |
| Hooks | .cursor/hooks.json, .cursor/hooks/*.sh | Shell / write / MCP / session / stop gates calling controlkeel validate when available. |
| MCP | .cursor/mcp.json | Stdio MCP; use ${workspaceFolder} for command paths and CK_PROJECT_ROOT. |
| Plugins | .cursor-plugin/ | Distributable bundle (plugin.json, mirrored assets, hooks/hooks.json, mcpServers) for Plugins → Install / marketplace-style flows. |
Install path: run controlkeel setup and controlkeel attach cursor in the governed repo root, then enable the local ControlKeel MCP server in Cursor and (if desired) install the generated .cursor-plugin from the repo or a release export. The generated marketplace-style bundle is not itself a public marketplace listing. Finish with controlkeel attach doctor, controlkeel provider doctor, controlkeel status, and controlkeel findings.
Run objective, repeatable improvement work under an immutable verifier and hard iteration, cost, time, and no-progress limits. Use for approved experiments with an automated metric and sandboxed worker.
Write concise, calm technical responses whose structure matches the decision, evidence, or sequence being communicated. Use when drafting substantial plans, reviews, findings, documentation, or completion summaries.
Operate inside a ControlKeel-governed session. Use this before code edits, shell execution, delegation, deploy work, or any task that needs CK validation, findings, budget, proof, or routing context.
Keep a governed session within budget. Use this before long-running agent work, bulk processing, or any task where spend pressure could change the plan.
Close a governed work session with validation, proof, findings, budget, digest, learning, and handoff checks. Use when the user asks to wrap up, stop for the day, or leave work ready for another agent.
Audit tests that may pass without proving the claimed behavior. Use for periodic test-quality reviews or when coverage looks healthy but regressions still escape.