omniagents-reviewer

Plugin omniagents-reviewer from marketplace omniagents in gao-hongnan/omniagents. Commands read from the repo's manifest — 12 days ago.

Skills (7)

• correctness-review

  Use when reviewing code for logic errors, type-safety violations, null/undefined handling, off-by-one, race conditions, incorrect API usage, broken contracts, missing error handling, edge-case gaps, or state-management bugs. Trigger for correctness code review: logic bugs, type mismatches, unchecked

• design-review

  Use when reviewing code for maintainability issues such as coupling, cohesion, abstraction leaks, boundary drift, code smells, naming problems, duplicated logic, premature generalization, or design-pattern misuse. Trigger for design code review: high coupling, low cohesion, leaky abstraction, unclea

• operability-review

  Use when reviewing code for operability issues such as missing or noisy logging, absent metrics or tracing on new code paths, unreported errors, unbounded timeouts or retries, unsafe migrations, missing rollout/rollback paths, ungraceful shutdown, or config and secrets handling problems. Trigger for

• performance-review

  Use when reviewing code for performance issues: algorithmic complexity, N+1 queries, unnecessary allocations, unbounded concurrency, cache misuse, blocking I/O in async context, hidden materialization, ReDoS, cold-start cost, missing database indexes, connection pool exhaustion, or memory leaks. Tri

• review-contract

  Use when producing or consuming structured code review findings. Defines the shared output contract, severity rubric, finding schema, per-specialist report shape, and final aggregated report shape that all reviewer specialist agents must follow and the verifier agent enforces. Trigger for any review

• security-review

  Use when reviewing code for security vulnerabilities: injection (SQL, command, template, log), authentication/authorization gaps, secrets in code, unsafe deserialization, path traversal, SSRF, dependency vulnerabilities, cryptographic misuse, data exposure, or OWASP Top 10 patterns. Trigger for secu

• testing-review

  Use when reviewing code for test adequacy issues such as missing regression coverage, weak assertions, brittle mocks, fixture misuse, untested edge cases, snapshot overuse, flaky timing, or tests that miss user-visible behavior. Trigger for testing review: missing tests, no regression test, weak ass

Slash commands (2)

• /omniagents-reviewer:doctor

  Verify the reviewer plugin's wiring — skill preloads resolve, dimensions are

• /omniagents-reviewer:review

  Triage the diff, dispatch only the reviewer specialists it needs, verify

Subagents (8)

• adjudicator

  Evidentiary adjudication agent for the reviewer plugin. Receives the verifier's merged review report, re-opens every BLOCKER and IMPORTANT citation in the actual code, independently re-verifies the evidence, and confirms, downgrades, or drops each finding. Produces the final review report. The last

• correctness

  Correctness specialist reviewer. Reviews diffs, files, or branches for logic errors, type-safety violations, null/undefined handling, race conditions, broken contracts, missing error handling, and edge-case gaps. Produces structured findings in the review contract format. Does not write or patch cod

• design

  Design and maintainability specialist reviewer. Reviews diffs, files, or branches for coupling, cohesion, abstraction leaks, misplaced boundaries, naming problems, SOLID violations, unnecessary indirection, code smells, and design-pattern misuse. Produces structured findings in the review contract f

• operability

  Operability specialist reviewer. Reviews diffs, files, or branches for silent failure modes, missing logging/metrics/tracing, unbounded timeouts and retries, unsafe migrations, missing rollout/rollback paths, ungraceful shutdown, and config/secrets handling. Produces structured findings in the revie

• performance

  Performance specialist reviewer. Reviews diffs, files, or branches for algorithmic complexity issues, N+1 queries, unnecessary allocations, unbounded concurrency, cache misuse, blocking I/O in async context, hidden materialization, and cold-start cost. Produces structured findings in the review cont

• security

  Security specialist reviewer. Reviews diffs, files, or branches for injection vulnerabilities, authentication/authorization gaps, secrets in code, unsafe deserialization, cryptographic misuse, data exposure, SSRF, path traversal, and dependency vulnerabilities. Produces structured findings in the re

• testing

  Testing specialist reviewer. Reviews diffs, files, or branches for missing regression coverage, weak assertions, brittle mocks, untested edge cases, fixture misuse, snapshot overuse, flaky async/time behavior, and tests that do not exercise user-visible behavior. Produces structured findings in the

• verifier

  Verification and aggregation agent for the reviewer plugin. Receives raw findings from all specialist agents (correctness, security, performance, design, testing), deduplicates findings at the same file:line, cross-validates overlapping concerns, normalizes numeric confidence, filters unsupported or

Similar plugins