Skip to content

great_cto

v2.39.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo 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

Governance phases add implementation briefs, traceability graphs, and gap‑closure waves.

Changes in this release

Feature Low

Adds impl-brief handoff bundle with allowlist/denylist and API contract validation.

Adds impl-brief handoff bundle with allowlist/denylist and API contract validation.

Source: llm_adapter@2026-06-06

Confidence: high

 —
Feature Low

Adds traceability engine linking requirements, use cases, tasks, and tests via `/trace` command.

Adds traceability engine linking requirements, use cases, tasks, and tests via `/trace` command.

Source: llm_adapter@2026-06-06

Confidence: high

 —
Feature Low

Adds gap-closure wave framework with interim signed exceptions for deferred gaps.

Adds gap-closure wave framework with interim signed exceptions for deferred gaps.

Source: llm_adapter@2026-06-06

Confidence: high

 —
Performance Low

Adds 63 new unit tests, increasing total test coverage to 120 lib tests.

Adds 63 new unit tests, increasing total test coverage to 120 lib tests.

Source: llm_adapter@2026-06-06

Confidence: high

 —
Full changelog

NaCl-inspired governance: impl-brief + traceability + gap-closure waves (Phases 3–5)

Completes the governance contour started in v2.38.x (Phase 1 signed exceptions · Phase 2
strict-mode evidence-blocking gates). All logic is machine-checkable with $0, no new
runtime deps, lean (no Neo4j). 63 new unit tests (120 lib total).

Phase 3 — impl-brief handoff bundle. Each senior-dev task ships a per-task brief that
pins files-to-modify (allowlist) / files NOT to modify (denylist) / API-CONTRACT /
TEST-SPEC / ACCEPTANCE, so scope creep is caught mechanically, not in review prose.

  • skills/great_cto/templates/IMPL-BRIEF-template.md + scripts/lib/impl-brief.mjs
    (parseBrief / validateBrief / checkScope — glob **, denylist = hard fail). CLI
    check <brief> <changed-files…> exits 1 on a denylist hit.
  • pm Step 7b emits + validates; senior-dev Step 4 reads, Step 6b refuses an out-of-scope
    commit (override = signed exception); architect derives the denylist from ARCH Non-goals.

Phase 4 — requirement → use-case → task → test traceability + /trace. NaCl's graph
value (impact analysis + coverage gaps) modelled on beads relationships.

  • scripts/lib/trace.mjs (traceUp rationale / traceDown impact / coverageGaps) +
    /trace <id> | feature <slug>; /review trace is now a thin alias for the one engine.
  • architect mirrors REQ + UC into bd and wires task→uc→req; qa-engineer wires test→impl.

Phase 5 — gap-closure waves. Adopt strict gates on a legacy repo incrementally instead
of blocking cold: enumerate gaps, schedule into waves (criticals never deferred), hold each
deferred gap green with an interim signed, expiring exception — never a silent bypass.

  • scripts/lib/gap-waves.mjs (planWaves / interimExceptionsNeeded / validateRegister) +
    GAP-REGISTER / GAP-WAVE-PLAN templates; /audit step 4b + /migrate step 3b emit them.
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]