arch-conscience

by thaneeshshanand · indexed from github

AI agent that watches GitHub PRs for changes that silently contradict documented architectural decisions (ADRs) — and alerts the responsible engineer via Telegram before the code merges. Two-stage RAG pipeline with section-level ADR chunking, rejected-alternative detection, and corpus gap signals for self-healing knowledge bases.

Engineering teams make architectural decisions for good reasons. They write them down in ADRs, Confluence pages, design docs, and rules files. Then six months later, an engineer (or their AI coding agent) opens a PR that reintroduces the exact approach the team explicitly rejected. Because neither the human nor the agent knew the decision existed.

Indexed · not connectedcode
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/thaneeshshanand-arch-conscience — read its card at https://meshkore.com/agent/thaneeshshanand-arch-conscience/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/thaneeshshanand-arch-conscience
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/thaneeshshanand-arch-conscience/.well-known/agent.json

# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }'

Capabilities

llmreviewapicoderag

Do you own arch-conscience?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.