Skip to content

great_cto

v2.80.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 23d AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agentic-coding claude-code-plugin claude-code-skills claude-code-subagents code-review cto
+2 more
multi-agent sdlc

Summary

AI summary

Added interactive self‑upgrade prompt and improved detection of installation method.

Full changelog

Self-upgrade

  • great-cto upgrade --self — upgrades the CLI in place, detecting how it was
    installed from the running binary's realpath: npx cache (nothing to do — npx
    always runs latest), volta, pnpm, or npm with the exact global prefix derived
    from the binary path. On machines with more than one npm prefix it upgrades the
    binary that is actually running and prints which prefix was updated, then
    verifies old → new.
  • Interactive update prompt — when a newer version exists and you're in a real
    terminal, the update hint becomes a one-time Update to X.Y.Z? [Y/n] (15s
    timeout = No, asked at most once per release via promptedFor in the cache).
    Non-TTY, CI, and protocol commands (mcp) keep the silent one-line hint, which
    now recommends great-cto upgrade --self.
  • README highlights npx great-cto@latest as the zero-maintenance path for
    occasional use.
  • Tests: CLI suite 229 → 264 (+35); board/root 198.
View diff on GitHub

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

Share on X Share on Bluesky

Track great_cto

Get notified when new releases ship.

Sign up free

About great_cto

Engineering-management layer of 34 specialist AI agents covering the full SDLC (architect, PM, senior-dev, reviewer, QA, security, devops, L3-support + 18 archetype-specific reviewers) with auto-detected archetypes and compliance gates (PCI-DSS, HIPAA, FedRAMP, GDPR, EU AI Act). Runs in Claude Code, Cursor, Codex CLI, Aider, and Continue via AGENTS.md + MCP. MIT.

All releases →

Related context

Earlier breaking changes

  • v2.72.2 Removes Autopilot sidebar item and Operate topbar button from dev board.
  • v2.55.0 Hard-gates the Build board; redirects invite sessions to Operate for operators.
  • v2.43.0 Runtime now blocks autonomous execution of irreversible actions without prior human checkpoint.
  • v2.43.0 Adds reversible and blastRadius fields to every flow step.
  • v2.32.0 Removed AgentShield scanner and its CLI commands.

Beta — feedback welcome: [email protected]