CLAUDE LABJP
MCPSPEC — Claude now supports the MCP 2026-07-28 spec, which moves from a bidirectional stateful protocol to request/response so servers can run on serverless and edge infrastructureAUTHZ — The new spec strengthens OAuth and OIDC authorization and splits Apps and Tasks out into versioned extensionsSDK400 — MCP SDK downloads passed 400 million per month, roughly a 4x increase over the yearFORK — /fork copies your conversation into a new background session, so you can try a second approach without pausing the firstMCPLOGIN — claude mcp login authenticates a configured MCP server from your shell instead of the interactive /mcp menu, and claude mcp logout clears the stored credentialsREVIEWBG — /code-review now runs in the background, so the conversation keeps moving while the review worksMCPSPEC — Claude now supports the MCP 2026-07-28 spec, which moves from a bidirectional stateful protocol to request/response so servers can run on serverless and edge infrastructureAUTHZ — The new spec strengthens OAuth and OIDC authorization and splits Apps and Tasks out into versioned extensionsSDK400 — MCP SDK downloads passed 400 million per month, roughly a 4x increase over the yearFORK — /fork copies your conversation into a new background session, so you can try a second approach without pausing the firstMCPLOGIN — claude mcp login authenticates a configured MCP server from your shell instead of the interactive /mcp menu, and claude mcp logout clears the stored credentialsREVIEWBG — /code-review now runs in the background, so the conversation keeps moving while the review works
TAG

Unattended automation

8 articles
Back to all tags
Related:
Claude Code8Sonnet 52MCP1CI/CD1Operations1Permissions1Plan Mode1Security1background sessions1indie development1observability1session management1
Claude Code/2026-07-29Advanced

The MCP Server Connects Fine and Still Hands Back Zero Tools — Catching Silent Capability Drift with a Tool Manifest Diff

A missing credential does not break the MCP handshake. initialize succeeds, tools/list succeeds, and the array comes back empty. Here is the measured behaviour, and a preflight that locks the expected tool surface and fails closed before the agent ever starts.

Claude Code/2026-07-18Advanced

I Believed Plan Mode Only Read — Replacing That Belief With Machinery

Claude Code 2.1.212 fixed a bug where plan mode ran file-modifying Bash commands without the permission prompt or the SDK canUseTool callback. Here is what could happen while that assumption was broken, how to verify your own setup, and how to stop leaning on a mode name for safety.

Claude Code/2026-07-07Advanced

My background session sat at running all night — adding heartbeats to the agents view

The Claude Code agents view finally lets you see every background session at once, but a running badge is not proof of progress. Here is the external heartbeat layer I built to catch a silently stalled session in minutes instead of the next morning, with real numbers and the traps I hit.

Claude Code/2026-07-06Advanced

Which Nightly Job Wrote This Commit? Threading a Correlation Key Through Claude Code's Readable Session Names

When you run unattended nightly jobs across several repositories, you lose track of which session produced which commit. Here is how I redesigned Claude Code's readable session names into a correlation key that ties commits, logs, and sessions into a single thread — with real numbers.

Claude Code/2026-07-04Advanced

A 1M Context Window Is the New Default — So I Built an Admission Policy Instead of Filling It

Sonnet 5 is now the Claude Code default and native 1M context is standard. The hard errors disappeared, but a quieter kind of degradation took their place. Here is how I made it visible with a probe, plus an admission policy and an effective-token-cost view — with working code and my own measurements.

Claude Code/2026-07-02Advanced

Which Model Ran Last Night's Unattended Session? Building Model Attribution and Default-Drift Detection After the Sonnet 5 Switch

Claude Code's default model switched to Sonnet 5, and unpinned headless runs changed models silently. Here is a working design for extracting the actual model from run output, appending an atomic run record, and deciding per task lineage whether to pin or follow the default.

Claude Code/2026-07-01Advanced

Don't Accept an Agent's Numbers and Citations As-Is — A Verification Gate Built on a Dedicated Auditor Subagent

A design that verifies every number and citation in an agent-generated summary using a separate subagent before accepting it — with working TypeScript for deterministic recomputation and fail-closed source matching.

Claude Code/2026-06-28Advanced

When You Fan Out Streaming Sessions, Your Laptop's CPU Gives Out First — An Adaptive Throttle That Caps Concurrency by Measured Load

Even with lighter streaming, fanning out many sessions on one machine saturates the host CPU before anything else. Here is why a fixed semaphore fails, plus a working adaptive gate that raises and lowers concurrency from measured CPU.