great_cto

v2.65.0 Feature

This release adds 3 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

Summary

AI summary

Adds support for Anthropic's Fable 5 model and an agent‑model override in the config.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds support for Anthropic's Fable 5 model (`claude-fable-5`). Adds support for Anthropic's Fable 5 model (`claude-fable-5`). Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Medium	Introduces `agent-model: fable` override in `~/.great_cto/config` to pin agents to Fable 5. Introduces `agent-model: fable` override in `~/.great_cto/config` to pin agents to Fable 5. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Medium	Recognizes `fable` / `claude-fable-5` as the newest deepest tier in lint policy, accepted where Opus is allowed. Recognizes `fable` / `claude-fable-5` as the newest deepest tier in lint policy, accepted where Opus is allowed. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Medium	Board agent runner passes `--model` verbatim, enabling `claude-fable-5` without additional changes. Board agent runner passes `--model` verbatim, enabling `claude-fable-5` without additional changes. Source: llm_adapter@2026-06-10 Confidence: high	—
Bugfix
Bugfix	Low	Verifies agent-model override e2e: repins to `model: fable` and rejects invalid values. Verifies agent-model override e2e: repins to `model: fable` and rejects invalid values. Source: llm_adapter@2026-06-10 Confidence: high	—
Bugfix	Low	Ensures lint tier policy correctly handles 6/6 Fable 5 cases. Ensures lint tier policy correctly handles 6/6 Fable 5 cases. Source: llm_adapter@2026-06-10 Confidence: high	—
Bugfix	Low	Confirms library compatibility: 348/348 tests pass with Fable 5. Confirms library compatibility: 348/348 tests pass with Fable 5. Source: llm_adapter@2026-06-10 Confidence: high	—

Full changelog

Adds support for Anthropic's newest model, Fable 5 (claude-fable-5):

Agent-model override — agent-model: fable in ~/.great_cto/config pins every managed agent/command to Fable 5 (alongside opus|sonnet|haiku).
Lint tier policy — fable / claude-fable-5 recognised as the newest deepest tier: accepted anywhere the policy allows opus; still flagged for haiku-only utility agents.
The board agent runner passes --model through verbatim, so claude-fable-5 already works there with no change.

Verified: override e2e (repins to model: fable, rejects bogus values), 6/6 lint tier cases, lib 348/348.

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.