SkyNET-agents
claudeDelegate work from Claude Code to Codex, Antigravity, OpenRouter or local Ollama, routed by live usage, as tracked background jobs.
1 skill · 7 commands · 4 agents
Four-lens code review (simplicity, functionality, security, maintainability), with fresh-context local subagents or a tribunal of external AI coding harnesses, merged into one verified, deduplicated report.
Plugin SkyNET-review from marketplace SkyNET-marketplace in CornelB/SkyNET-marketplace. Commands read from the repo's manifest — 5 days ago.
review-engineInternal engine for /review-board:review. Hard constraints, run directory layout, the scripts that build the scope and run the tribunal, the seat contract and the seat setup. Loaded by the review command; not meant to be invoked directly.
/skynet-review:resultList review-board runs, print a run's report (or the seat reports so far while a tribunal runs), or cancel a running tribunal.
/skynet-review:reviewReview a PR or a branch through four lenses (simplicity, functionality, security, maintainability), either with fresh-context local subagents or with an external tribunal of AI coding harnesses, and synthesize one report.
/skynet-review:statusShow which review-board tribunal seats are available or disabled (and why), and which Claude and codex models apply right now. Read-only.
functionality-reviewerLens "functionality" of review-board. Grumpy, no benefit of the doubt: business logic, edge cases, requirements and claim verification (VERIFIED / FALSE / UNPROVABLE), existence checks for every symbol, package, flag and path, and tests that really fail. Loads its instructions from the assembled len
maintainability-reviewerLens "maintainability" of review-board. Readability, naming against the repo's own conventions, and documentation accuracy (comments and docs describe what the code does). Loads its instructions from the assembled lens prompt file the orchestrator names.
security-reviewerLens "security" of review-board. Read-only security audit: findings only above 80% confidence with a concrete attack path. Loads its instructions from the assembled lens prompt file the orchestrator names.
simplicity-reviewerLens "simplicity" of review-board. KISS: finds what the change can lose and still do its job (dead code, yagni, hardening for load the repo does not have, wrappers, duplication), and never asks for more code. Loads its instructions from the assembled lens prompt file the orchestrator names.
Delegate work from Claude Code to Codex, Antigravity, OpenRouter or local Ollama, routed by live usage, as tracked background jobs.
1 skill · 7 commands · 4 agents
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
Use Codex from Claude Code to review code or delegate tasks.
3 skills · 8 commands · 1 agent · hooks
Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work with both LanceDB Embedded and LanceDB Enterprise.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.