containment-protocol
Client-side React/TypeScript SPA. Pure simulation in `src/domain/`; Zustand store in `src/app/store/`; projections in `src/features/*View.ts`; UI in `src/features/**/*.tsx`. **MUST** read before reviewing: - PR body **Linear** section (SPE-#### slice issue, parent/child, scope boundary)
Install / Use
npx skills add JamesJedi420/containment-protocolInstalls into whichever agent you are using.
Amazon Q Rules
Amazon Q Developer rules
Quality Score
Category
Project & Program ManagementSupported Platforms
Skill content
View source on GitHubContainment Protocol — review policy
Client-side React/TypeScript SPA. Pure simulation in src/domain/; Zustand store in src/app/store/; projections in src/features/*View.ts; UI in src/features/**/*.tsx.
MUST read before reviewing:
- PR body Linear section (SPE-#### slice issue, parent/child, scope boundary)
planning/spe-*-slice.mdwhen the PR implements a sliceAGENTS.mdReview guidelines
Severity
Flag P0/P1: correctness bugs, determinism breaks, persistence/hydration gaps, layer-boundary violations, week-close ordering errors, hidden state leaked through UI, event schema/migration regressions, missing tests when acceptance requires coverage, security issues.
Do NOT flag: style-only nits, drive-by refactors, scope expansion, pre-existing npm run build baseline TypeScript drift unless this PR makes it worse.
Scope
- One Linear slice per PR; match slice Goal and Acceptance.
- Prefer the smallest in-boundary fix in suggestions.
- Do not request unrelated refactors or parallel subsystems.
- Do not wire vendor search/scan SaaS into
src/or CI without an explicit Linear slice (docs/agent-cursor-plugins.md). Prefer required Sonatype before npm add/upgrade; Snyk is optional.
Re-review
After material fixes on an existing PR, automatic review may not re-run. Suggest /q review in a new top-level PR comment when appropriate.
Related Skills
headroom
73.4kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
ruflo
73.0k🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Memori
16.9kMemori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
opencodex
15.8kUniversal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Security Score
Audited on Invalid Date
