coverloop
FeaturedThe multi-agent coding loop that covers every angle — one model builds, independent AI models review it from every direction, tests decide, you hold the final gate. Privacy-enforced, anti-drift, self-improving.
Install
Plugins install via a marketplace, in two steps.
This plugin isn't listed in a marketplace we've indexed. Install it directly from its GitHub repository — the README has the setup steps.
View on GitHubBundles
Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.
Skills (3)
coverloop-contract
The Coverloop operating contract — how much verification a change must earn before it ships. Load this BEFORE writing or reviewing code in a repo that uses Coverloop (has a .coverloop/ directory or a CLAUDE.md carrying PROTOCOL_VERSION), and whenever deciding a risk tier, choosing reviewers, or about to push/merge/migrate/deploy.
multimodel-review
Review a focused diff or snippet with the multi-model loop — GLM (full-ZDR) red-team + MiniMax M3 (data_collection:deny) second auditor — then reconcile by convergence/divergence. Use when reviewing a non-trivial diff before Codex/merge, or to sanity-check the loop. Never send secrets or whole-repo context.
reflect-and-save
At the end of a meaningful task, reflect on what was learned and save durable lessons to memory (the self-improving loop / "periodic nudge"). Use after finishing a non-trivial task, a fix, a decision, or when the user gives feedback worth keeping. Skip on trivial/conversational turns.
Hooks (5)
Quality Score: 76/100
Details
- Author
- danielsimisi-coder
- Repository
- danielsimisi-coder/coverloop
- Created
- 2 months ago
- Last Updated
- 6 days ago
- Language
- Python
- License
- MIT