Agent Claude Code
Enforces "AI queryability by default". Use when a change adds or modifies durable, user-relevant data. Checks the feature is discoverable and actionable through search, agent tools, and MCP — or that a waiver is documented.
Agent Claude Code
Reviews analytics coverage and telemetry privacy. Use when a feature adds runtime behavior, or when analytics events or telemetry helpers change. Treats missing analytics on a new feature as a correctness issue, and PII in product analytics as a defect.
Command Claude Code
Add privacy-safe analytics for a feature, per STANDARD.md's Analytics section.
Agent Claude Code
Adversarial reviewer for database access control, migrations, privileged credentials, and data exposure. Use proactively before merging any change that touches migrations, access policies, auth helpers, or grants.
Command Claude Code
Scaffold a new migration with safety defaults — never edit an existing one.
Agent Claude Code
Reviews UI changes against the repo's design system and checks that critical UI flows carry browser evidence. Use when a change adds or modifies UI, layout, components, or styling.
Agent Claude Code
Adversarial reviewer for auth boundaries, secret handling, injection paths, and privilege escalation. Use proactively before merging any change that touches auth, privileged access, external input parsing, CI workflows, or agent-facing surfaces.
Agent Claude Code
Lead quality reviewer that runs this repo's STANDARD.md completion checklist end to end. Use before finalizing or opening a PR for any change with product behavior.
Command Claude Code
Open a concise, team-lead-ready PR following STANDARD.md.
Command Claude Code
Run the right checks for the current change and report honestly.
Skill Claude CodeCodex
Engineering judgment for writing code that stays cheap to change — simplicity, naming, boundaries, duplication, tests. Apply to any feature work, refactor, API design, or architecture decision, in any language.
Skill Claude CodeCodex
Review code changes against this repo's STANDARD.md. Use when reviewing a PR, a diff, or another agent's work — enforces the review order, the comment quality bar, and severity discipline.
Skill Claude CodeCodex
Apply this repo's STANDARD.md while implementing, refactoring, or fixing. Use for any change that affects product behavior — before editing, while verifying, and when reporting done.
Agent Claude Code
Resolves actionable review feedback on the existing story branch.
Agent Claude Code
Turns a story into an implementation-ready plan grounded in the repository.
Agent Claude Code
Implements a complete story and proves the result in the real development environment.
Agent Claude Code
Diagnoses and repairs an eligible CI failure on the existing pull-request branch.
Agent Claude Code
Reviews a story pull request from a fresh context and reports actionable findings.
Agent Claude Code
Audits current repository changes and dependencies for actionable security risks.
Skill Claude CodeCodex needs its repo
Set up and launch an autonomous research project with Limina. Use when the user wants a persistent research agent workflow with hypotheses, experiments, findings, and review artifacts.
Skill Codex
Build, review, refactor, or design software for readability, simplicity, modularity, testability, and safe changeability. Use for feature work, architecture decisions, API boundaries, naming, refactors, and code reviews across any language or stack.
Skill Codex
Design, review, and conclude rigorous research experiments for Limina's H→E→F workflow. Use when creating or revising hypotheses, experiments, or findings; defining baselines, datasets, metrics, or stopping rules; comparing candidate methods; deciding whether a result is conclusive; or when a negative result may be…
Skill Codex
Map the AI/ML state of the art for a concrete technical problem. Use for exploratory research, mechanism-based literature search, benchmark mapping, and finding generalizable approaches. Not for simple fact lookup.
Skill Codex needs its repo
Challenge the current Limina research direction and next-step plan. Use for step-back reviews, pre-commitment checkpoints, plateau reviews, contradictory findings, or pivot/continue/stop recommendations when evidence or framing may be weak.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: