Skip to content

great_cto

v2.87.1 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

adapt now ends with a Next block that routes users to appropriate entry points based on their tool context.

Full changelog

adapt points forward instead of back at itself

With the telemetry Worker redeployed (its ?days=all + lifetime block had been
written on 2026-06-26 and never shipped), the real usage shape became visible for
the first time: 100 recorded runs, adapt 69 of them against board 2. People
run adapt, come back, run it again.

The cause was in the command's own last words — both closing lines pointed at
adapt ("Re-run after editing PROJECT.md…", "add other AI tools…") and nothing
pointed forward. The command taught its own loop.

  • adapt now ends with a Next: block. Claude Code users get the three real
    entry points (/audit, /start, /inbox) plus the board.
  • The block is tool-aware: adapt is the one command that serves
    non-Claude-Code users (Cursor / Copilot / Windsurf / Aider), and the agent
    pipeline is Claude-Code-only. Sending a Cursor user to /audit would be a dead
    end — worse than saying nothing. Those users are instead told plainly what
    they have and the concrete step that unlocks the rest.
  • nextStepsAfterAdapt is a pure function, so the routing is tested without
    generating files. 7 tests; 288/288 CLI suite green.

Telemetry Worker: deployed (version f8f69cf9) — ?days=all and lifetime totals
now respond as documented.


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]