This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Summary
AI summaryAll agent instruction templates now automatically call analyze_codebase("/src/") on first connection.
Full changelog
What's new
All four agent instruction templates now include analyze_codebase("/src/<project>") in the Session Setup. When an AI agent (Cursor, Claude Code, VS Code Copilot) connects for the first time, it automatically calls this tool and gets a structural overview of the codebase — zero tokens, zero cloud.
Process flow
Agent connects → set_project() → get_recent_sessions()
↓
Sessions empty? (first time)
↓ yes
analyze_codebase("/src/<project>")
↓
Read report: top files, categories, duplicates
↓
Start working with full context
Files updated by the installer
| File | Environment |
|------|-------------|
| AGENTS.md | Claude Code, generic agents |
| .cursor/rules/flaiwheel.mdc | Cursor |
| CLAUDE.md | Claude Code |
| .github/copilot-instructions.md | VS Code / GitHub Copilot |
Upgrade
curl -sSL https://raw.githubusercontent.com/dl4rce/flaiwheel/main/scripts/install.sh | bash
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About dl4rce/flaiwheel
Self-hosted memory and governance layer for AI coding agents. 28 MCP tools with structured knowledge capture, hybrid search (semantic + BM25 + cross-encoder reranking), behavioral documentation nudges, cold-start codebase analyzer, and git-native storage. Single Docker container, zero cloud dependencies.
Related context
Beta — feedback welcome: [email protected]