A six-phase refactoring workflow that forces codemapping, coverage checks, and test verification after every single change.
Turns a vague or large request into one decision-complete work plan: explores the codebase first, asks only the real forks, and writes the plan only after your explicit okay.
Analyzes a codebase and auto-generates a hierarchy of AGENTS.md files at the root and in the directories that actually deserve one.
Spawns up to 16 parallel agents right before an npm publish to audit changes, breaking changes, and the correct version bump.
Wires the mnemon graph memory binary into NanoClaw agent containers so agents recall past context across sessions.
Analyzes every open issue and PR in parallel and writes evidence-backed triage reports — without ever mutating GitHub.
Installs an Ollama MCP server so the NanoClaw container agent can call — and optionally manage — local LLMs.
A step-by-step debugging playbook for NanoClaw's containerized agent runtime — logs, session DBs, mounts and auth failures.
Reroutes a NanoClaw agent group to a local Ollama model instead of the Anthropic API — no provider code required.
Picks up after `migrate-v2.sh` to seed the owner, move legacy memory, reconcile container configs, and port v1 fork customizations.
Extracts your NanoClaw fork's customizations into a replayable migration guide and reapplies them on a clean upstream checkout — no merge conflicts.
A guided runbook that merges upstream NanoClaw changes into your customized fork with backups, conflict previews, validation and breaking-change migrations.
Convenes your git worktrees and open PRs as chat agents, runs the discussion in rounds, and lands on one consolidation plan.
Turns Claude into an explore-first planning consultant that grounds in your repo, asks only the real owner-decisions, and writes one decision-complete plan after you approve.
Teaches Claude to ship web apps with the vercel CLI and manage projects, domains, and env vars safely.
Opt NanoClaw out of the OneCLI gateway and inject Anthropic credentials straight from .env into the container.
Turns the agent into a planning consultant that explores the codebase first, asks only the genuine decisions, and writes one decision-complete work plan after your explicit approval.
Debugs, fixes and verifies a LazyCodex or Codex defect in a throwaway workspace, then ships it as a fork PR or a patch-embedded verified-fix issue.
Keeps polling a pull request's CI checks, comments, and unresolved review threads until it's genuinely ready to merge.
Turns a feature request into a phased, doc-verified implementation plan where each phase can be executed in a fresh chat session.