Skip to content

great_cto

v2.40.0 Feature

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

✓ 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

great_cto pivots to AI autopilots for business across seven verticals with a measurable quality scorecard.

Full changelog

AI autopilots for business — service-autopilot verticals, a quality scorecard, and the positioning pivot

The big one: great_cto becomes "AI autopilots for business" — products that sell the outcome
of a service, not a tool to a specialist. Seven verticals, a measured quality scorecard, and a
full positioning pivot. 49 new lib tests since v2.39.0 (189 total); structural + 21 reviewers green.

Service-autopilot family (epic great_cto-rpd). A cross-cutting overlay + six vertical packs,
each a full reviewer + threat-model template + pack + command + measured human-sign-off gate:

  • service-autopilot-pack + scripts/lib/autopilot-gate.mjs — the four autopilot invariants made
    machine-checkable: judgment boundary (confidence→escalation), accuracy-as-SLA, per-decision audit
    trail, per-outcome unit economics.
  • legaltech (UPL · privilege · e-sign · gate:attorney-signoff), rcm (ICD-10/CPT · False
    Claims Act · NCCI · gate:coding-signoff), procurement (OFAC sanctions · FCPA · fraud/SoD ·
    gate:payment-release), accounting (GAAP/ASC 606 · SOX ICFR · gate:financial-close),
    msp (change-mgmt · JIT/PAM · SOC 2 · gate:change-approval), tax (Circular 230 ·
    §6694/6695/7216 · gate:preparer-signoff). 21 domain reviewers wired.

Vertical quality scorecard (epic great_cto-h6n). Measure each vertical 0–100 — quality is
earned, not declared.

  • scripts/lib/vertical-score.mjs (7 weighted dimensions) + scripts/eval/vertical-scorecard.mjs
    (golden + adversarial cases through the reviewer + LLM judge) + a regression gate
    (--gate/--rebaseline) wired into ai-eval-engineer. Two measure→improve→re-measure cycles
    lifted legaltech 85→94.75 and msp 78→98.5. All seven verticals ship-ready on a measured basis.

Autopilot pivot (epic great_cto-og7). Positioning moves from packs/pipelines to flows.

  • flows/*.flow.json (single source of truth) + scripts/lib/flow.mjs + scripts/lib/connectors.mjs
    (connector catalog, all sandbox stubs) + /flow command + docs/positioning/vocabulary.md.
  • /start detects the business function → renders the flow; README leads with the autopilots.
    Packs / reviewers / gates are now the under-the-hood trust layer, never the headline.

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

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]