By sebdysart
Multi-repo AI ecosystem plugin — cross-repo grounding, anti-slop enforcement, and proactive business evolution for Claude Code
Execute the bounded automation plan generated by review-pr. Runs on generated branches and never mutates protected branches directly.
Run business evolution analysis. Finds gaps, bottlenecks, and competitive deficiencies, then presents ranked improvement suggestions with evidence.
Full ecosystem health audit. Computes per-repo and overall health scores across test coverage, code quality, dead code, and TODO burden.
Analyze the cross-repo impact of uncommitted changes. Shows ripple effects across all configured repositories.
Resolve owner assignments for repos, APIs, paths, and packages using omni-link ownership rules.
Reviews changes for cross-repo safety. Verifies API contracts, type lineage, and dependency compatibility across repository boundaries.
Business intelligence agent operating from a CTO/product strategist perspective. Researches industry best practices, analyzes competitive landscape, and provides strategic improvement roadmaps.
Deep-dive single repository analysis agent. Explores code structure, traces dependencies, identifies dead code, analyzes test coverage gaps, and reports on repo health in detail.
Critic agent that examines generated code for hallucinated imports, phantom packages, unverified API calls, and placeholder patterns. Returns a structured PASS/FAIL verdict.
Iron law quality gate that BLOCKS (not warns) on hallucinated imports, unknown packages, wrong conventions, and placeholder code. Enforcement, not suggestion.
Surface business improvement opportunities backed by codebase evidence. Runs evolution analysis at session start and on-demand via /evolve.
Detect and enforce codebase conventions during code generation. Covers naming, file organization, error handling, and testing patterns.
Analyze cross-repo impact before making changes to APIs, schemas, or shared types. Run impact analysis to see ripple effects.
Navigate cross-repo dependencies to answer "Where is X used?", trace dependency chains, and assess change impact.
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executes directly as bash, bypassing the AI model
Executes directly as bash, bypassing the AI model
Local-first multi-repo engineering control plane for Claude Code -- semantic cross-repo analysis, PR/MR intelligence, bounded automation, policy enforcement, and ecosystem-level evolution.
omni-link scans up to 10 repositories, builds a branch-aware ecosystem graph of APIs, types, dependencies, ownership, runtime signals, and policy state, then uses that graph to drive scans, impact analysis, health scoring, PR/MR review artifacts, provider publishing, and bounded execution planning.
This is not just a repo scanner. In max-tier mode, omni-link behaves like a local-first ecosystem control plane:
review-pr emits risk, owners, policy decisions, contract mismatches, and execution plans.publish-review supports dry-run, replay, GitHub, and GitLab transports with capability negotiation and live metadata hydration.apply and rollback stay branch-oriented, emit rollback plans, and now produce an execution ledger for auditability.node_modules.The current repository state is validated by npm run verify:stress, which includes lint, typecheck, unit/integration tests, coverage, build, CLI smoke, max-tier smoke, contract fixtures, package-install smoke, full stress, and live-provider gates when credentials are configured.
Current proof points from the verified state:
488 core tests passing, plus live GitHub and GitLab provider tests executed in sandbox PR/MR flows90.6% statement coverage0 moderate-or-higher audit vulnerabilities8 repos and 6 languages in one engine runclaude plugin install omni-link
git clone https://github.com/Sebdysart/omni-link.git
cd omni-link
npm install
npm run build
HustleXP-tailored multi-repo engineering control plane for Claude Code with docs authority, Swift↔tRPC bridge analysis, phase-drift gating, and communication-pro-max orchestration (structured handoff, Agent Teams bridge, MCP message bus)
npx claudepluginhub sebdysart/omni-linkAutomated code review for pull requests using multiple specialized agents with confidence-based scoring
Codebase exploration, refactoring, and quality analysis
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
Review pull requests with structured analysis and approve with confidence
Codebase intelligence for Claude Code. Indexes your codebase into five layers (Graph, Git, Docs, Decisions, Code Health) and exposes them through nine task-shaped MCP tools — so Claude understands architecture, ownership, hotspots, why code is built the way it is, and where the defect risk lives.
Multi-agent code review for Claude Code — parallel review by Codex (GPT-5.5), Gemini 3.1 Pro, and five Claude specialist subagents (one run blind), then verified synthesis.