DSH Auto Review
PerryLink/dsh-auto-review · skills
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approva.
★ 148GitHub stars
0Forks
2026-08-17Last updated
TypeScriptLanguage
Apache-2.0License
Key features
- Second-model AI approval for DeepSeek Harness — a read-only reviewer subagent decides allow/deny on the approval chain, fail-closed by default.
- The host registers an autoReview session projection (folded from the log-only autoReview/ events) and serves it through the session-projection channel.
- The answerer runs at its registration position in the waterfall: if a human UI answerer is composed BEFORE the auto-review row, humans answer first and the reviewer only sees what is delegated downstream.
- Permissionsthe workshop manifest declares session:append, approval:answer, subagent:spawn, command:register, and tools:observe.
- When an action crosses the sandbox boundary, a second model reads the evidence and returns a verdict with a reason — so humans approve nothing while nothing unsafe slips through.
Requirements
- The reviewer needs a working LLM route (inherited by default)
- without one every review falls back per fallbackPolicy — never a silent grant.
Install command
dsh plugin --profile web add github:PerryLink/dsh-auto-review