great_cto

v2.73.1 Feature

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

Published 1mo AI Agents & Assistants

View tool

✓ 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

Affected surfaces

auth breaking_upgrade

Summary

AI summary

Fixed monitor steps to use read operations instead of unintended writes.

Changes in this release

Type	Severity	Summary	CVE
Feature	Medium	Added explicit `connector:op` support for tools (backward compatible). Added explicit `connector:op` support for tools (backward compatible). Source: llm_adapter@2026-06-13 Confidence: high	—
Feature	Medium	Introduced `check-status` operation to `irs-efile`. Introduced `check-status` operation to `irs-efile`. Source: llm_adapter@2026-06-13 Confidence: high	—
Bugfix	High	Corrected monitor steps to use read operations instead of unintended write operations. Corrected monitor steps to use read operations instead of unintended write operations. Source: llm_adapter@2026-06-13 Confidence: high	—

Full changelog

Systemic fix: flow steps referenced a connector by id only, so the runner defaulted to its FIRST capability — a WRITE op for write-capable connectors. 10 monitor steps were re-running the irreversible write (e.g. rcm monitor → clearinghouse:submit-837 instead of fetch-835). Idempotency guarded real double-submission, but it was semantically wrong.

Tools now accept explicit connector:op (backward compatible). Fixed 10 monitor steps to read ops; added check-status to irs-efile.
Phase 4 Wave 1 (rcm + live FHIR/EHR) verified end-to-end: live FHIR + NLM code-sets + NCCI → gate → approve → live 837 submit; irreversible write only after a signature.
Tests: flow-connector-ops (3); all 25 flows valid. Follow-on great_cto-nl5 for 8 pre-gate cases.

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.

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

Related tools

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.