Agent Workflow Skills is a library of Claude Code skills, subagents and hooks for an agent that proves its work. A supervisor sends each step to the cheapest model that can do it and escalates after two failures, gates pass on exit code, bug fixes ship with a test shown to fail without the fix, and every session ends with a handoff note the next one picks up.
Be the first to rate Agent Workflow Skills. Your feedback helps other users decide.
The new test is run against the code from before the fix and shown to fail, then pass with it.
A session ends with a handoff note that the next session picks up automatically.
A supervisor routes each step to the cheapest model and moves up a tier after two failures.
Similar tools in the same category — compare side-by-side
Glider is a single-node vector database that treats S3-compatible object storage as the source of tr...
Shipback is an SFTP deploy tool built so every deploy can be taken back. It uploads a folder to cPan...
SuperLocalMemory is an open-source, local-first memory control plane for AI agents and teams. One me...
Guides and comparisons about code tools
Nine Show HN launches beneath the model: filesystems, snapshots, gateways and deploy tools that decide what an agent sees and what survives.
A 2026 guide to AI code tools for data science: GitHub Copilot, Codeium, CodeWhisperer, Cursor, Codium AI, Replit, Noteable, Hugging Face, LangChain, Phind,
Three shifts have changed what AI does for developers, from autocomplete to repo-wide edits to review agents. What each category is actually good for.
An honest 2026 look at AI bug-fixing tools: Codium AI (Qodo), BugHunter AI, DeepCode, GitHub Copilot, and why a human must verify the fix.
A 2026 comparison of AI API-testing tools: AutoTest AI, TestGuard AI, APIBuilder AI, Bito. Covers E2E tests, auto-docs, and why human review still matters.
