{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"hn-46388882","slug":"a-claude-code-plugin-that-catch-destructive-git-an","name":"A Claude Code plugin that catch destructive Git and filesystem commands","type":"skill","url":"https://github.com/kenryu42/claude-code-safety-net","page_url":"https://unfragile.ai/a-claude-code-plugin-that-catch-destructive-git-an","categories":["code-review-security"],"tags":["hackernews","show-hn"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"hn-46388882__cap_0","uri":"capability://safety.moderation.destructive.command.detection.for.git.and.filesystem.operations","name":"destructive command detection for git and filesystem operations","description":"This capability monitors user inputs for potentially destructive Git commands and filesystem operations by leveraging a pattern-matching engine that identifies specific keywords and command structures. It integrates with the Claude Code plugin architecture, allowing it to intercept commands before execution, providing a safety net for users. The unique aspect is its real-time analysis of command syntax, which can differentiate between safe and unsafe operations based on context.","intents":["How can I prevent accidental data loss when using Git?","What tools can help me avoid running dangerous filesystem commands?","How do I ensure my Git commands are safe before executing them?"],"best_for":["developers working with Git and filesystem commands in collaborative environments"],"limitations":["May not catch all edge cases of destructive commands due to reliance on predefined patterns","Performance may vary based on command complexity"],"requires":["Claude Code plugin installed","Git CLI installed"],"input_types":["text","code"],"output_types":["text","alerts"],"categories":["safety-moderation","developer-tools"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"hn-46388882__cap_1","uri":"capability://safety.moderation.contextual.command.alerting","name":"contextual command alerting","description":"This capability provides contextual alerts when a user attempts to execute a potentially harmful command by analyzing the command's context and user history. It uses a combination of heuristics and user-defined safety preferences to determine the severity of the command and offers suggestions for safer alternatives. This proactive approach helps prevent mistakes before they happen.","intents":["How can I get warnings before executing risky commands?","What alternatives can I use for destructive commands?","How do I customize alerts for my specific workflow?"],"best_for":["individual developers and teams looking to enhance their command safety"],"limitations":["Customization options may be limited to predefined templates","Alerting may introduce slight delays in command execution"],"requires":["Claude Code plugin installed","User-defined safety preferences set"],"input_types":["text","code"],"output_types":["text","alerts"],"categories":["safety-moderation","user-experience"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":32,"verified":false,"data_access_risk":"high","permissions":["Claude Code plugin installed","Git CLI installed","User-defined safety preferences set"],"failure_modes":["May not catch all edge cases of destructive commands due to reliance on predefined patterns","Performance may vary based on command complexity","Customization options may be limited to predefined templates","Alerting may introduce slight delays in command execution","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.58,"quality":0.14,"ecosystem":0.36,"match_graph":0.25,"freshness":0.9,"weights":{"adoption":0.15,"quality":0.25,"ecosystem":0.1,"match_graph":0.45,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:23.326Z","last_scraped_at":"2026-05-04T08:10:06.239Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=a-claude-code-plugin-that-catch-destructive-git-an","compare_url":"https://unfragile.ai/compare?artifact=a-claude-code-plugin-that-catch-destructive-git-an"}},"signature":"f/rEneF0J5xfIMSix4+4BPOiJMMDmeh64oOxhpXQ5pAP3BTRS6jUpcCpbQ/i/EKtzqN+WCbxG1tw9QzzHGYADQ==","signedAt":"2026-06-15T06:49:50.922Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/a-claude-code-plugin-that-catch-destructive-git-an","artifact":"https://unfragile.ai/a-claude-code-plugin-that-catch-destructive-git-an","verify":"https://unfragile.ai/api/v1/verify?slug=a-claude-code-plugin-that-catch-destructive-git-an","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}