Seven-release stretch from v2.1.107. Two headline shifts: v2.1.113's CLI now spawns a native per-platform binary instead of bundled JS (tighter supply chain, faster cold start). And v2.1.111's /fewer-permission-prompts skill scans transcripts to propose a prioritized settings allowlist — the first feature that actually cuts Claude Code's biggest daily friction. Plus fullscreen TUI, /ultrareview cloud PR review, Opus 4.7 xhigh effort, 1-hour prompt caching, proxy auth helper protocol for Kerberos/SSO (5 vars), Agent Teams scaffolding, experimental Advisor Tool. 20 new env vars, 1 new model ID, ~80 bug fixes.
2 new env vars, 0 removed. Enterprise TLS certificate store control (CLAUDE_CODE_CERT_STORE) — OS CA store trusted by default, bundled reverts to Node.js CAs. SDK OAuth refresh coordination (CLAUDE_CODE_SDK_HAS_OAUTH_REFRESH) prevents double-refresh races in IDE extensions. /team-onboarding command. /ultraplan auto-provisioning. Command injection fix in LSP binary detection. Virtual scroller memory leak fix. Hardcoded 5-minute timeout removed.
0 new env vars, 0 removed. Bedrock auth hotfix — fixed 403 "Authorization header is missing" regression from v2.1.94 when using AWS_BEARER_TOKEN_BEDROCK or CLAUDE_CODE_SKIP_BEDROCK_AUTH. Binary extraction byte-identical to v2.1.94. Mantle auth layer still stabilizing. v2.1.95 skipped.
5 new env vars, 0 removed. Mantle auth proxy for Amazon Bedrock (CLAUDE_CODE_USE_MANTLE) with skip flag. Sandbox state flag (CLAUDE_CODE_SANDBOXED). MCP server environment variable allowlist replaces all-or-nothing env inheritance. Team onboarding flows. --resume across worktrees. CJK text corruption fix. Write tool diff 60% faster.
1 new env var, 2 removed. MCP 500K character tool result persistence override. Plugin bin/ executable support — native binaries in plugins. disableSkillShellExecution setting locks down skill shell access. Multi-line deep links. Edit tool token optimization with shorter old_string anchors. CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION replaces typo predecessor.
3 new env vars, 1 new command. Anthropic AWS as fifth API provider (CLAUDE_CODE_USE_ANTHROPIC_AWS) with IAM ambient auth skip. Offline-resilient marketplace plugin caching. /powerup interactive lessons. Prompt-cache regression fix since v2.1.69. Quadratic SSE transport and transcript write fixes. PowerShell security hardening. Auto mode now respects explicit user constraints.
2 new env vars, 2 removed. Net count flat at 202. OAuth console override completes the auth triptych. Trusted device token for persistent sessions. MCP server env vars removed after 2 versions. Cowork Dispatch delivery fix plus model selection. Boris Cherny's 15 hidden features thread. --bare default flip coming.
6 new env vars, 1 removed. MCP server multiplexing with CLAUDE_CODE_MCP_SERVER_NAME and CLAUDE_CODE_MCP_SERVER_URL. OAuth endpoint overrides for enterprise identity providers. PowerShell parse timeout. Binary shrank 7.15 MB by replacing WASM yoga-layout (yes, flexbox in your terminal) with pure TypeScript. Conditional hook if fields. Scheduled task timestamps. Memory leak patches.
6 new env vars. Idle session management with configurable thresholds, stream watchdog timeout. Bedrock/Vertex/Foundry capability override env vars. TaskCreated and WorktreeCreate HTTP hooks. Deep links open in preferred terminal. PowerShell tool preview. MCP 2KB cap and deduplication. Stats screenshot (Ctrl+S in /stats). Windows drive root protection.
Karpathy calls it AI psychosis. Frank Contrepois calls it agentic fever. But what's really happening is the same thing that happened during the gold rush — five forces driving a collective fever that goes far beyond individual compulsion.
Ramp's CPO Geoff Charles demoed building a production feature in 5 minutes on camera. Voice of Customer and Analyst agents collapsed days of work into minutes. 50% AI-written code heading to 90%. Three lessons every engineering org needs now.
The --bare flag strips Claude Code to its core for scripted -p calls — no hooks, LSP, plugins, or auto-memory. Concurrent OAuth fix ends the multi-session re-auth nightmare (#24317). Channels permission relay, /btw pasted text fix, ! bash mode discoverability. Plan mode hides clear context. 17 bug fixes.
Channels research preview turns Claude Code into a persistent agent reachable from Telegram and Discord. Simplified plugin install, inline settings declarations, 80MB memory reduction for large repos. Fine-grained streaming fix retires the CLAUDE_CODE_ENABLE_FINE_GRAINED_TOOL_STREAMING=0 workaround. 7 bug fixes.
Looking at the last three Claude Code releases (v2.1.77–v2.1.79), the pattern isn't what Anthropic is building — it's what they're deleting. 25+ bug fixes, three sandbox security holes closed, 18MB startup memory eliminated, and two feature flags removed. Constant pruning as competitive advantage.
CLAUDE_CODE_ATTRIBUTION_HEADER controls the x-anthropic-billing-header in Claude Code API requests. Setting it to 0 fixes Bedrock 400 errors and broken prompt caching with proxies like claude-code-router and liteLLM. Plus: the critical difference between this env var and git attribution settings.
Control when Claude Code compacts your conversation history. Covers the ~83% cap bug, recommended values by use case, related compaction env vars, and troubleshooting. The definitive guide to CLAUDE_AUTOCOMPACT_PCT_OVERRIDE.
3 new env vars, 2 removed: subprocess environment scrubbing for security, extra API metadata for enterprise routing, refactored init path saving 18MB startup memory. Console auth for API billing, non-streaming fallback timeout, 10+ bug fixes.
The definitive reference for every Claude Code environment variable — 500+ vars organized by category. API keys, model overrides, Bedrock/Vertex/Foundry setup, feature flags, context compaction, agent teams, MCP, plugins, enterprise proxy, OTEL, and more. Includes the fix for the Bedrock eager_input_streaming 400 error.
1 new env var and 1 renamed slash command: cowork memory extra guidelines for multi-agent teammate sessions, /branch (renamed from /fork), and /copy N index. Largest stabilization release tracked — 25+ bug fixes spanning terminal rendering, tmux, teammate sessions, and memory management.
3 new env vars and 1 new slash command: account tagged IDs for multi-tenant billing, fast-mode network error resilience, workspace host path mappings for containers, and /effort for interactive effort level control. Headline feature: MCP elicitation support for bidirectional server communication.
2 new env vars and 1 new slash command: auto-compact window threshold for 1M context windows, plugin option prefix for CI/CD configuration, and /color for session-level prompt-bar customization.
Small release with 2 new env vars and 1 removal: frame timing diagnostics, session-end hooks timeout, and the two-stage classifier flag graduated to default.
Maintenance release with no env var changes. First version where we tracked the full slash command inventory built into the Claude Code binary — 22 commands established as our baseline.
Engineers no longer write code — they design environments where agents do. A practical guide to agent legibility, automated invariants, and treating AI as first-class teammates.
Static analysis tools have guarded codebases for decades, yet critical vulnerabilities still ship. The collaboration between Anthropic and Mozilla shows what happens when LLMs move from generating code to actively defending it.
We analyze every Claude Code release to document undocumented environment variables, feature gates, and model IDs. Track all versions from v2.1.19 to latest.
Minor release with 3 new env vars: CCR v2 bridge protocol toggle, force-enable effort level, and delta MCP instruction updates. Plus one removal. Continuing the binary extraction series.
Open-source CLI that scans all your Claude Code sessions, groups safe commands with AI, and applies them globally — so you stop re-approving npm test, git add, and pnpm build every session.
I reran my binary extraction on Claude Code v2.1.69 — 50 versions after the original v2.1.19 analysis. The count nearly doubled: 165 env vars, 16 model IDs, 41 feature gates. New plugin system, mTLS support, background tasks, context compaction controls, and multi-provider auth.
crashpull is a zero-dependency CLI that pipes Firebase Crashlytics into your terminal and AI agents. List crashes, read stack traces, resolve — all from npx.
I found 83 undocumented environment variables in Claude Code 2.1.19's binary. None are in the official docs. Highlights include Agent Swarms, Plan v2 agent controls, debug/profiling flags, and ways to disable features like CLAUDE.md loading.
Gas Town is Steve Yegge's toolkit for running multiple AI coding agents in parallel. I tried it. Here's what happened: the Mayor, the polecats, the freaky feeling, and 20+ tasks on a $100 Claude plan.
Context window mismanagement is the number one productivity killer in Claude Code. This guide shows you how to recognize context degradation, why it happens around 70-75% capacity, and the exact strategies top engineers use to maintain peak Claude Code performance throughout long coding sessions.
After using Claude Code extensively across dozens of projects, I've refined a workflow that maximizes autonomy while maintaining control over critical decisions. The /task command represents years of iteration—a structure that consistently delivers better results than ad-hoc prompting or even the built-in questionnaire system introduced in Claude Code 2.0.25+.
Claude Code versions 2.0.22 through 2.0.25 had nasty bugs. Instead of waiting for a fix, I dug into the source code and found powerful undocumented environment variables for debugging, autocompaction, and log control.
I've been using the official schema from Anthropic for Claude Code settings, but one thing was missing: autocomplete for environment variables. So I built an improved schema with 50+ env vars, inline documentation, and full IntelliSense support. Plus, I'm launching a new 'Extras' section for downloadable productivity tools.
Claude Code, the terminal-native, agentic coding assistant, gets exponentially more useful when you give it a concise project guide (CLAUDE.md), set sensible permissions & environment via settings.json, and automate routine actions with slash-command files. This guide packs all three into copy-ready snippets: stack-specific CLAUDE.md templates, a JIRA-driven custom workflow, permission hygiene tips, and a reflection command that continuously sharpens your guide.
A space for curious devs and knowledge workers who want to work smarter, not just stay busy. Every week, I try out new AI-powered tools and share honest takeaways with short posts, clear language, and zero hype.