CLAUDE LABJP
CODE — Claude Code has moved on to v2.1.267. It was v2.1.263 yesterday, so four releases landed in the space of a single dayEFFORT — A new maxEffortLevel setting caps the effort level across every provider, Bedrock, Vertex and Foundry included. People can still choose something lowerCACHE — The largest part of this release is not a feature at all. More than a dozen fixes address cases where prompt cache reuse quietly brokeRESUME — Resuming a session or switching models with /model could rewrite the tool definitions, and the only visible symptom was a bill that crept upwardGATEWAY — v2.1.266 undoes a regression. Setups carrying CLAUDE_CODE_USE_GATEWAY were failing every request. The fix is the upgrade itself, not a config changePLUGIN — --plugin-dir now accepts a folder of plugins, and a path containing a backslash can no longer slip past the containment check on macOS or LinuxCODE — Claude Code has moved on to v2.1.267. It was v2.1.263 yesterday, so four releases landed in the space of a single dayEFFORT — A new maxEffortLevel setting caps the effort level across every provider, Bedrock, Vertex and Foundry included. People can still choose something lowerCACHE — The largest part of this release is not a feature at all. More than a dozen fixes address cases where prompt cache reuse quietly brokeRESUME — Resuming a session or switching models with /model could rewrite the tool definitions, and the only visible symptom was a bill that crept upwardGATEWAY — v2.1.266 undoes a regression. Setups carrying CLAUDE_CODE_USE_GATEWAY were failing every request. The fix is the upgrade itself, not a config changePLUGIN — --plugin-dir now accepts a folder of plugins, and a path containing a backslash can no longer slip past the containment check on macOS or Linux
TAG

Context Design

5 articles
Back to all tags
Related:
Claude Code5indie development2Agent Skills1Plugins1Indie Development1hooks1automation1quality gates1SKILL.md1progressive disclosure1subagents1code review1
Claude Code/2026-09-10Intermediate

One plugin.json turns a shelf of skills into something you can switch off as a group

When I sorted my skills by what work they belong to, the set I open almost daily turned out to be 5 percent of the total. Here is how I dropped a .claude-plugin/plugin.json into each group so I could switch a whole shelf off, plus the two loading rules I tripped over on the way.

Claude Code/2026-08-28Intermediate

Don't let your verification script's full output flow back through a hook

The check was working the whole time. The conversation was what ran out of room. Measured side by side: 58 bytes from one scan of 833 files, 42KB from another. Which paths actually reach the model, and how to enforce a budget on them.

Claude Code/2026-08-20Advanced

The Biggest Section in Your SKILL.md Is Usually the One to Keep

A skill I run every week cost about 10K tokens just to load. Measuring it section by section showed why the largest block was the one I had to leave in place, and what splitting by reach actually saved.

Claude Code/2026-08-17Advanced

Now that forking is the default, review agents are the ones I still call by name

Subagent forking became the default, so delegated work now inherits the parent conversation. Work can inherit context. Judgment cannot. Here is how I declare that boundary in the repository and catch it drifting.

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.