RepoJournal
Anthropic @anthropics
150 wires and counting

$ follow Anthropic

Keep up with Anthropic in about 3 minutes: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

fair warning: these emails are deeply technical. diffs, version numbers, CVEs, benchmark deltas. if that's not your idea of a good read, this isn't your newsletter.

Folds into your digest — weekly by default, monthly if you prefer. Unsubscribe in one click.

$ status

wire 2026-06-08
stories 41
GitHub RSS Archive Reviews

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

CLAUDE CODE 2.1.169 SHIPS WITH SAFE MODE AND WORKSPACE NAVIGATION

By RepoJournal · Filed · About Anthropic · Composed from the cited sources · methodology

github-actions[bot]
1 person shipped this
github-actions[bot] @github-actions[bot] 5 cited

Claude Code's latest release adds troubleshooting tools that let you disable customizations on the fly and move sessions between directories without breaking the prompt cache.

Claude Code v2.1.169 [1] introduces three developer-facing features: a `--safe-mode` flag that disables all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) for debugging, a `/cd` command to switch working directories mid-session without losing cached context, and a `disableBundledSkills` setting to hide built-in skills from the model. The Agent SDK [2] and claude-code-action [3] both shipped synchronized updates to match, with the Agent SDK now bundling CLI 2.1.169 and the action bumping both Claude Code and Agent SDK to their latest versions [4]. The plugin ecosystem saw five routine dependency bumps across qdrant-skills [5], sentry-cli [6], codspeed [7], expo [8], and oracle-ai-data-platform-workbench-spark-connectors [9], all validated through automated workflows but pending manual review before merge.

Action items

References

  1. [1] v2.1.169 ↗ anthropics/claude-code
  2. [2] v0.2.94 ↗ anthropics/claude-agent-sdk-python
  3. [3] v1.0.141 ↗ anthropics/claude-code-action
  4. [4] chore: bump Claude Code to 2.1.169 and Agent SDK to 0.3.169 ↗ anthropics/claude-code-action
  5. [5] bump(qdrant-skills): 11df00a7 → 82337ccd ↗ anthropics/claude-plugins-official
  6. [6] bump(sentry-cli): 329f5c5d → 9e9fe0fb ↗ anthropics/claude-plugins-official
  7. [7] bump(codspeed): 9793aaf9 → c6112f16 ↗ anthropics/claude-plugins-official
  8. [8] bump(expo): 145a923c → c3886024 ↗ anthropics/claude-plugins-official
  9. [9] bump(oracle-ai-data-platform-workbench-spark-connectors): 04cc355f → 00cedef3 ↗ anthropics/claude-plugins-official

$ ls anthropics/reviews/ # the step-back reads

the week in review Claude Code symlink TOCTOU allows arbitrary file write the month in review Sandbox and SDK holes dominate Anthropic's September
Full archive → Weekly reviews →

Quick answers

What shipped in Anthropic on June 8, 2026?
Claude Code's latest release adds troubleshooting tools that let you disable customizations on the fly and move sessions between directories without breaking the prompt cache. In total, 5 commits, 33 pull requests, and 3 releases landed.
Who contributed to Anthropic on June 8, 2026?
1 developer shipped this update, including github-actions[bot].
What were the notable Anthropic updates?
v2.1.169, v0.2.94, and v1.0.141.
♥

$ log @anthropics --recent

sandbox-runtime fixes a quadratic glob parse, and five projects enroll in OSS Scanner 52 shipped buffa breaks inferred collect() calls, sandbox-runtime fixes the proxy and Linux relays 120 shipped Buffa hardens codegen and descriptor validation, OSS Scanner enrolls WordPress and the AT Protocol stack 26 shipped security-guidance findings reach stderr, and sandbox ignoreViolations types match the CLI 28 shipped

$ log --all # elsewhere on the wire

Alignment & Post-training verl rejects conflicting vLLM engine_kwargs, open-instruct adds MILES OPD behind a Megatron learner Interpretability nnsight 0.8.0 cuts import time from 7.6s to 1.6s

$ ls showcases/

Safety Evals AI Red Teaming Agent Security Interpretability Alignment & Post-training

$ init your-desk

RepoJournal can write one of these for any repo you care about. Sign in with GitHub, pick your repos and sources, and your desk gets a wire like this one every morning.