docs: tighten contribution guidance and vision links

CONTRIBUTING.md

@@ -5,6 +5,7 @@ Welcome to the lobster tank! 🦞
 ## Quick Links
 
 - **GitHub:** https://github.com/openclaw/openclaw
+- **Vision:** [`VISION.md`](VISION.md)
 - **Discord:** https://discord.gg/qkhbAGHRBT
 - **X/Twitter:** [@steipete](https://x.com/steipete) / [@openclaw](https://x.com/openclaw)
 
@@ -51,7 +52,7 @@ Welcome to the lobster tank! 🦞
 - Test locally with your OpenClaw instance
 - Run tests: `pnpm build && pnpm check && pnpm test`
 - Ensure CI checks pass
-- Keep PRs focused (one thing per PR)
+- Keep PRs focused (one thing per PR; do not mix unrelated concerns)
 - Describe what & why
 
 ## Control UI Decorators

VISION.md

@@ -6,6 +6,7 @@ It runs on your devices, in your channels, with your rules.
 This document explains the current state and direction of the project.
 We are still early, so iteration is fast.
 Project overview and developer docs: [`README.md`](README.md)
+Contribution guide: [`CONTRIBUTING.md`](CONTRIBUTING.md)
 
 OpenClaw started as a personal playground to learn AI and build something genuinely useful:
 an assistant that can run real tasks on a real computer.
@@ -30,6 +31,8 @@ Next priorities:
 - Ergonomics across CLI and web frontend
 - Companion apps on macOS, iOS, Android, Windows, and Linux
 
+Contribution rule: PRs must be single-focused and should not mix unrelated concerns in one change.
+
 ## Security
 
 Security in OpenClaw is a deliberate tradeoff: strong defaults without killing capability.
@@ -49,6 +52,8 @@ Core stays lean; optional capability should usually ship as plugins.
 Preferred plugin path is npm package distribution plus local extension loading for development.
 If you build a plugin, host and maintain it in your own repository.
 The bar for adding optional plugins to core is intentionally high.
+Plugin docs: [`docs/tools/plugin.md`](docs/tools/plugin.md)
+Community plugin listing + PR bar: https://docs.openclaw.ai/plugins/community
 
 Memory is a special plugin slot where only one memory plugin can be active at a time.
 Today we ship multiple memory options; over time we plan to converge on one recommended default path.
@@ -92,6 +97,7 @@ It is widely known, fast to iterate in, and easy to read, modify, and extend.
 - Commercial service integrations that do not clearly fit the model-provider category
 - Wrapper channels around already supported channels without a clear capability or security gap
 - First-class MCP runtime in core when `mcporter` already provides the integration path
+- Agent-hierarchy frameworks (manager-of-managers / nested planner trees) as a default architecture
 - Heavy orchestration layers that duplicate existing agent and tool infrastructure
 
 This list is a roadmap guardrail, not a law of physics.