#permissions
GitHub repositories that have self-applied the topic "permissions" — a creator-tagged metadata that surfaces how AI projects describe themselves.
REPOS Repos for #permissions (top 6 by stars)
Cross-agent permission policy for AI coding agents. MCP sync daemon, CLI, codecs, and evaluator. One .agents/permissions.json for every agent.
Evander764/auto-agree-permissionsPortable permission automation and bootstrap for Claude Code and Codex.
TecniartGalicia/handsfree-claude-codeAutonomous mode for Claude Code in one command: native settings only, no hooks, no quotas. Plus a Doctor that explains why Claude keeps asking for permission. Not affiliated with Anthropic.
erikolson/cpermComposable Claude Code permissions; define reusable permission modules, compose them per-project, and detect drift.
wangxing-git/dsh-autogateDeepSeek Harness 自动审批插件：在 workspace-write 沙箱之上叠加确定性规则 + LLM 安全审批，自动模式不放宽沙箱、fail-closed。 Safe auto-approval for DeepSeek Harness — deterministic rules + LLM review on top of the workspace-write sandbox. Auto mode without ever granting full-access.
taltara/capmarkCapability manifests for AI agent plugins. Declare what a plugin may do, in Markdown, and check it.
RELATED Other topics · full topics ranking →
#claude-code
1,555#ai-agents
1,156#llm
1,066#claude
936#python
802#ai
737#developer-tools
723#mcp
719#codex
517Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology