Plugins

Native interactive Git diff review for DeepSeek Harness with structured annotations sent back to the current Agent session.

DSH GitHub connector: review PRs, triage issues, debug CI, prepare changes (18 tools, gh-first + REST fallback, approval-gated writes).

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

DeepSeek Harness (dsh) plugin for @tabilo/ai-code-review: registers the ai_code_review tool (review | context) that reuses the Node.js engine to collect diffs, run tests/coverage, do impact analysis, and feed pack skills to the model.

Deterministic code security review: 40+ rules, secret entropy detection, staged-diff review, SARIF export, baseline acceptance, SBOM-lite dependency inventory and health self-check.

Headless Claude Code consultations with advisor, reviewer, and designer roles, returned as reference answers.

Structured code review skill for DeepSeek Harness -- bugs, security, performance, style

On-demand code review for DeepSeek Harness.

Workspace-scoped Git graph with history search and diffs, multi-worktree WIP and agent-session views, and guarded Git operations with recovery refs.

Quality suite: background tsc --noEmit diagnostics fed back after the agent edits TypeScript, plus a /code-review command running five parallel review lenses with confidence scoring; absorbs dsh-code-check and dsh-command-code-review.

Explicit, evidence-first multi-model consultation for DeepSeek Harness

Reports the semantic blast radius of agent code edits: which symbols changed, who calls them, and which of those callers have no covering test.

A session-scoped working-tree review panel for DeepSeek Harness

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.

Local AI code-review gate: review a workspace/branch/commit diff via the managed ocr.js, returning structured findings with token stats; gate mode fails on findings.