Second Model Passive Review Assistant
omdsh-dev/dsh-advisor · skills
A standalone dsh plugin bundle porting the omp "advisor" subsystem: a per-session reviewer model that observes the primary transcript, reviews each stepped turn with an.
★ 19GitHub stars
2Forks
2026-08-15Last updated
TypeScriptLanguage
MITLicense
Key features
- The advisor never approves or rejects the primary agent's actions
- Model capability & budgetthe advisor call runs with reasoningEffort: 'off' — sent only when the configured model's adapter declares that effort (deepseek models do
- it never issues commands as if it were the primary agent.
- Every delivered message is self-described advisory content, and a misbehaving reviewer is bounded end to end (emission guard, immuneTurns cooldown, failure policy) so it can never stall or pollute the primary loop.
- any other model gets the option omitted automatically, so non-reasoning providers keep working) — and a 5120-token output cap (a user-directed 20× supersession of the original 256).
Requirements
- The MVP deliberately drops full omp parity.
- Accepted gaps (tracked in the harness iteration roadmap)
Install command
dsh plugin --profile web add github:omdsh-dev/dsh-advisor