Claude Code-style permission rules engine: hard/deny/ask/allow tiers with a hard tier above full access, workspace-scoped rules, wildcard path protection, and a visual staged editor; rules persist in settings.yaml.
- License
- MIT
- Added
- 2026-08-16
GitHub info
- License
- MIT
- Primary language
- JavaScript
- Last push
- Aug 19, 2026, 6:57 AM
- Maintainer
- 940842546
- Added
- 2026-08-16
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
顶部概览
https://raw.githubusercontent.com/940842546/dsh-permissions/main/assets/01-permissions-overview.png
规则面板
https://raw.githubusercontent.com/940842546/dsh-permissions/main/assets/02-permissions-rules.png
草稿态
https://raw.githubusercontent.com/940842546/dsh-permissions/main/assets/03-permissions-draft.png
Install
dsh plugin --profile web add github:940842546/dsh-permissionsREADME badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/940842546/dsh-permissions)Related plugins
Security & Permissionsapi-relay-audit
★ 819Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.
dsh-pentest
★ 324Authorized pentest mode for DeepSeek Harness — exploration chain, assets and findings with a Web view.
dsh-auto-review
★ 120Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.