↓ Skip to main content

Publishing daily · 355 articles

Spec-Driven Development, Claude Code & Agentic Coding

Software development is shifting from writing code to writing specs. sdd.sh follows that shift as it happens — Spec-Driven Development, Claude Code, MCP, and the agentic workflows that let AI agents plan, build, test, and ship. Opinionated, practical, and unapologetically pro-Anthropic.

New here? Start with these
#

Explore by topic
#

Publishing daily. Subscribe — RSS or JSON Feed — so you don’t have to poll.

AI Tools

Claude Code v2.1.307: A Safety Event for Every Blocked Tool Call, and a One-Command API Migration

Claude Code v2.1.307 adds a claude_code.safety_event OpenTelemetry event for tool calls stopped, prompted or sent back by permission rules, auto mode, hooks or the sandbox, plus /claude-api api-version to move code to API version 2026-10-21. It also fixes HTTP MCP tool calls being sent twice. Changelog-only analysis; not run.

Oct 22, 2026 · 5 min read

Guides

Claude Code v2.1.305 and v2.1.306: A Sandbox Escape Hatch, a Smarter Retry Watchdog, and a Managed-MCP Behavior Change

Claude Code v2.1.305 adds an opt-in sandbox.allowNestedUserNamespaces setting, a usage-limit recheck for unattended retry mode, and a change to how allowedMcpServers treats managed stdio servers. v2.1.306 is two fixes. Changelog-only analysis: I did not run either release.

Oct 21, 2026 · 6 min read

Guides

Claude Code v2.1.304: A Guided Auto Mode Setup, Mods That Can't Be Auto-Approved, and a Warning Before You Burn Your 5-Hour Limit

Claude Code v2.1.304 adds /auto-mode-setup (now on Bedrock, Vertex and Foundry), lets a mod’s tool.check demand a human decision with decider: “person”, warns before resuming an old conversation eats your 5-hour limit, and ships a long list of fixes, including a worktree exit that could lose commits.

Oct 20, 2026 · 6 min read

Industry

Reflection's Beam: A 501B Open-Weight Coding Model You Can't Download Yet

Reflection AI announced Beam on October 5: a 501B-parameter sparse MoE (23B active) that it self-reports at 80.1 on Terminal-Bench 2.1 and 80.9 on SWE-bench Verified. Weights are promised for later in October, the license is not confirmed from Reflection’s own materials, and none of the numbers are independently verified.

Oct 18, 2026 · 4 min read

Guides

Claude Code v2.1.301–302: Unattended Retries, a Pickable Auto Mode Classifier, and Fork Subagents Everywhere

Claude Code v2.1.301 (Oct 15) and v2.1.302 (Oct 16) cap how long unattended retries wait on a usage limit, let you choose the client-side auto mode classifier’s model, turn fork subagents on by default outside the terminal, and limit concurrent prompt/agent hooks to 12 per event.

Oct 17, 2026 · 5 min read

AI Tools

GitHub Copilot Retires Six Models on October 19, and This Time None of Them Are Claude

On October 19, GitHub Copilot removes Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 from every Copilot surface. Replacements are Gemini 3.8 Flash, GPT-5.6 Sol and Luna, and Grok 4.6, auto-enabled for Business and Enterprise unless admins opted out.

Oct 16, 2026 · 4 min read

Guides

Claude Code Subagent Cost Controls: autoCompactWindow, Workflow Model Pinning, and Cache-Write Telemetry

Claude Code v2.1.296 lets a subagent auto-compact earlier than the main session and pins every workflow agent to one model; v2.1.300 splits OpenTelemetry cache writes into 5-minute and 1-hour buckets. Together they are the first real cost-control surface for multi-agent runs. Based on the changelog only; I have not tested these.

Oct 15, 2026 · 4 min read