plugin
Reduces context setup time and token waste by letting AI agents ingest entire repository state natively, enabling faster, more accurate code suggestions and …
Archcore gives coding agents the architecture, rules, and prior decisions of your repo — stored in Git as one source of truth — so changes land where the project says they belong. Slash commands cover setup (/archcore:init), loading decided context before edits (/archcore:context), documenting tribal knowledge (/archcore:capture), planning (/archcore:plan), recording decisions as enforced rules (/archcore:decide), and doc-drift audits (/archcore:audit). Works in Claude Code, Cursor, and Codex CLI; requires the Archcore CLI, which serves the MCP server the plugin talks to.
- Load the rules and prior decisions governing a file or your uncommitted changes before editing (/archcore:context --git-changes)
- Capture undocumented module, API, or pipeline knowledge into docs agents can use (/archcore:capture)
- Record an architecture decision with rationale and turn it into an enforced team rule (/archcore:decide)
Reduces context setup time and token waste by letting AI agents ingest entire repository state natively, enabling faster, more accurate code suggestions and architectural decisions without manual file selection.
Engineering teams using Claude or Cursor who need faster AI-assisted code reviews, refactoring, or feature implementation across large codebases.
https://github.com/archcore-ai/plugin
By archcore-ai
How to Get It
curl -fsSL https://archcore.ai/install.sh | bash # then in Claude Code: /plugin marketplace add archcore-ai/plugin && /plugin install archcore@archcore-plugins
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me load the rules and prior decisions governing a file or my uncommitted changes before editing (/archcore:context --git-changes)
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 31 GitHub stars; contributors unknown; last commit 1d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
- Single maintainer. Consider the risk if this person stops maintaining the project.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 31 GitHub stars; contributors unknown; last commit 1d ago; license Apache-2.0.