{"id":"527e8c20-e83c-4cb7-a075-e185ee241719","shortId":"Uh3EqS","kind":"skill","title":"Add a browser review checkpoint before risky agent actions with AgentClick","tagline":"Use AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI.","description":"# Add a browser review checkpoint before risky agent actions with AgentClick\n\nUse AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI.\n\n## Prerequisites\n\nAgentClick, browser access, npm, compatible local agent that can invoke tools and follow skill instructions\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- git clone https://github.com/agentlayer-io/AgentClick.git\n- npm install\n- npm run dev\n- npm run build\n\nRequirements and caveats from upstream:\n- For OpenClaw in particular, use a stronger model with solid instruction-following, since the workflow is skill-based and depends on the agent following routing instructions reliably.\n\nBasic usage or getting-started notes:\n- AgentClick works as a **skill / plugin** for modern AI agents. Any agent that can run local tools, send HTTP requests, and follow skill instructions can integrate with it.\n\n- Source: https://github.com/agentlayer-io/AgentClick\n- Extracted from upstream docs: https://raw.githubusercontent.com/agentlayer-io/AgentClick/HEAD/README.md\n\n## Documentation\n\n- https://github.com/agentlayer-io/AgentClick\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick/)","tags":["add","browser","review","checkpoint","before","risky","agent","actions","with","agentclick","skills","agentskillexchange"],"capabilities":["skill","source-agentskillexchange","skill-add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick","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/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick","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 (1,394 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":"2026-05-18T19:09:17.613Z","embedding":null,"createdAt":"2026-05-18T13:14:58.059Z","updatedAt":"2026-05-18T19:09:17.613Z","lastSeenAt":"2026-05-18T19:09:17.613Z","tsv":"'/agentlayer-io/agentclick':200,211 '/agentlayer-io/agentclick.git':119 '/agentlayer-io/agentclick/head/readme.md':207 '/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick/)':218 'access':90 'action':9,52 'add':1,44 'agent':8,16,51,59,94,157,178,180,213 'agentclick':11,13,54,56,88,169 'agentskillexchange.com':217 'agentskillexchange.com/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick/)':216 'ai':177 'approv':33,76 'base':152 'basic':162 'browser':3,42,46,85,89 'build':127 'built':41,84 'caveat':130 'chang':26,69 'checkpoint':5,48 'clone':116 'code':25,68 'command':21,64 'compat':92 'depend':154 'dev':124 'doc':204 'document':208 'draft':23,66 'edit':32,75 'environ':114 'exchang':215 'extract':201 'follow':100,145,158,190 'get':166 'getting-start':165 'git':115 'github.com':118,199,210 'github.com/agentlayer-io/agentclick':198,209 'github.com/agentlayer-io/agentclick.git':117 'http':187 'human':29,72 'inspect':31,74 'instal':103,107,121 'instruct':102,144,160,192 'instruction-follow':143 'integr':194 'invok':97 'local':93,184 'match':112 'model':140 'modern':176 'note':168 'npm':91,120,122,125 'openclaw':134 'particular':136 'path':110 'paus':18,61 'plan':22,65 'plugin':174 'prerequisit':87 'purpos':40,83 'purpose-built':39,82 'raw.githubusercontent.com':206 'raw.githubusercontent.com/agentlayer-io/agentclick/head/readme.md':205 'reject':35,78 'reliabl':161 'request':188 'requir':128 'review':4,47 'riski':7,20,50,63 'rout':159 'run':123,126,183 'send':186 'setup':109 'sinc':146 'skill':101,151,173,191,214 'skill-add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick' 'skill-bas':150 'solid':142 'sourc':197,212 'source-agentskillexchange' 'start':167 'stronger':139 'tool':98,185 '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' 'ui':43,86 'upstream':106,132,203 'usag':163 'use':12,55,104,137 'work':170 'workflow':148","prices":[{"id":"6ab6b764-d343-44ee-a969-d07b574f4bf8","listingId":"527e8c20-e83c-4cb7-a075-e185ee241719","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":"2026-05-18T13:14:58.059Z"}],"sources":[{"listingId":"527e8c20-e83c-4cb7-a075-e185ee241719","source":"github","sourceId":"agentskillexchange/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick","isPrimary":false,"firstSeenAt":"2026-05-18T13:14:58.059Z","lastSeenAt":"2026-05-18T19:09:17.613Z"}],"details":{"listingId":"527e8c20-e83c-4cb7-a075-e185ee241719","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick","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":"090721bfbe30899a9945a6037651ea0316a6c970","skill_md_path":"skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Add a browser review checkpoint before risky agent actions with AgentClick","description":"Use AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick"},"updatedAt":"2026-05-18T19:09:17.613Z"}}