{"id":"4379c738-b5c7-414b-9628-f3fc3419a968","shortId":"Cgh3Zu","kind":"skill","title":"Gate risky agent actions behind approval checkpoints with Latch","tagline":"Use Latch to put an MCP policy and approval layer between agents and tools so risky calls pause for review while safe calls continue automatically.","description":"# Gate risky agent actions behind approval checkpoints with Latch\n\nUse Latch to put an MCP policy and approval layer between agents and tools so risky calls pause for review while safe calls continue automatically.\n\n## Prerequisites\n\nDocker, Latch CLI, an upstream MCP server to wrap\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- git clone https://github.com/latchagent/latch\n- docker compose up -d\n- npx @latchagent/cli@latest run \\\n\nRequirements and caveats from upstream:\n- **Risky actions** (shell commands, external sends) → Require human approval\n- # Start Latch with Docker\n- Policy is evaluated (allow / deny / require approval)\n\nBasic usage or getting-started notes:\n- Security guardrails for AI agents. Safe actions run automatically. Risky actions wait for approval.\n- bash\n- cd latch\n\n- Source: https://github.com/latchagent/latch\n- Extracted from upstream docs: https://raw.githubusercontent.com/latchagent/latch/HEAD/README.md\n\n## Documentation\n\n- https://latch.mintlify.app/docs/introduction\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch/)","tags":["gate","risky","agent","actions","behind","approval","checkpoints","with","latch","skills","agentskillexchange","agent-skills"],"capabilities":["skill","source-agentskillexchange","skill-gate-risky-agent-actions-behind-approval-checkpoints-with-latch","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,191 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:10:32.161Z","embedding":null,"createdAt":"2026-05-18T13:16:38.920Z","updatedAt":"2026-05-18T19:10:32.161Z","lastSeenAt":"2026-05-18T19:10:32.161Z","tsv":"'/docs/introduction':167 '/latchagent/latch':95,156 '/latchagent/latch/head/readme.md':163 '/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch/)':174 'action':4,38,110,142,146 'agent':3,21,37,55,140,169 'agentskillexchange.com':173 'agentskillexchange.com/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch/)':172 'ai':139 'allow':125 'approv':6,18,40,52,117,128,149 'automat':34,68,144 'bash':150 'basic':129 'behind':5,39 'call':26,32,60,66 'caveat':106 'cd':151 'checkpoint':7,41 'cli':72 'clone':92 'command':112 'compos':97 'continu':33,67 'd':99 'deni':126 'doc':160 'docker':70,96,121 'document':164 'environ':90 'evalu':124 'exchang':171 'extern':113 'extract':157 'gate':1,35 'get':133 'getting-start':132 'git':91 'github.com':94,155 'github.com/latchagent/latch':93,154 'guardrail':137 'human':116 'instal':79,83 'latch':9,11,43,45,71,119,152 'latch.mintlify.app':166 'latch.mintlify.app/docs/introduction':165 'latchagent/cli':101 'latest':102 'layer':19,53 'match':88 'mcp':15,49,75 'note':135 'npx':100 'path':86 'paus':27,61 'polici':16,50,122 'prerequisit':69 'put':13,47 'raw.githubusercontent.com':162 'raw.githubusercontent.com/latchagent/latch/head/readme.md':161 'requir':104,115,127 'review':29,63 'riski':2,25,36,59,109,145 'run':103,143 'safe':31,65,141 'secur':136 'send':114 'server':76 'setup':85 'shell':111 'skill':170 'skill-gate-risky-agent-actions-behind-approval-checkpoints-with-latch' 'sourc':153,168 'source-agentskillexchange' 'start':118,134 'tool':23,57 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'upstream':74,82,108,159 'usag':130 'use':10,44,80 'wait':147 'wrap':78","prices":[{"id":"a700035e-49e0-46c4-831d-ebdd92add575","listingId":"4379c738-b5c7-414b-9628-f3fc3419a968","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:16:38.920Z"}],"sources":[{"listingId":"4379c738-b5c7-414b-9628-f3fc3419a968","source":"github","sourceId":"agentskillexchange/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch","isPrimary":false,"firstSeenAt":"2026-05-18T13:16:38.920Z","lastSeenAt":"2026-05-18T19:10:32.161Z"}],"details":{"listingId":"4379c738-b5c7-414b-9628-f3fc3419a968","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"gate-risky-agent-actions-behind-approval-checkpoints-with-latch","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"fbce62d705878dffde0a5458bc67f2103669d468","skill_md_path":"skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Gate risky agent actions behind approval checkpoints with Latch","description":"Use Latch to put an MCP policy and approval layer between agents and tools so risky calls pause for review while safe calls continue automatically."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/gate-risky-agent-actions-behind-approval-checkpoints-with-latch"},"updatedAt":"2026-05-18T19:10:32.161Z"}}