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 2026-07-27
stories 43
GitHub RSS Archive Reviews

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

PLUGIN VALIDATION SWEEP ACROSS THREE REPOS, 43 PRS MERGED

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

github-actions
1 person shipped this
github-actions @github-actions 14 cited

Automated SHA bumps for 14 plugins passed validation overnight across the official, community, and knowledge-work plugin repos, with every PR validated before merge.

The plugin ecosystem is moving in lockstep. Five plugins got bumped in claude-plugins-community [ref:1,2,3,4,5], four in knowledge-work-plugins [ref:6,7,8,9], and five in claude-plugins-official [ref:10,11,12,13,14]. Every bump went through claude plugin validate in its respective workflow before the PR opened. Carta-crm and wix advanced simultaneously across multiple repos, suggesting coordinated upstream releases. Hyperframes moved twice in the official repo within hours [ref:11,14], flagging either rapid iteration or a correction cycle. All 14 bumps remain unmerged pending manual review of scan jobs, holding the line on auto-merge discipline.

Action items

References

  1. [1] bump(adcp-client): 3d7b4b2a → e0562580 ↗ anthropics/claude-plugins-community
  2. [2] bump(ai-coding-ok): 1f9d3eed → c96068cd ↗ anthropics/claude-plugins-community
  3. [3] bump(ai-devkit): 116c3bb4 → 15b09d2d ↗ anthropics/claude-plugins-community
  4. [4] bump(aight): 7d582d0b → 09099471 ↗ anthropics/claude-plugins-community
  5. [5] bump(alps-writer): 8e2cedcb → ffa69ff5 ↗ anthropics/claude-plugins-community
  6. [6] bump(carta-crm): 62e9f9a0 → f57875b3 ↗ anthropics/knowledge-work-plugins
  7. [7] bump(wix): ca13a745 → 87c6b285 ↗ anthropics/knowledge-work-plugins
  8. [8] bump(wix): 3cff9cb0 → ca13a745 ↗ anthropics/knowledge-work-plugins
  9. [9] bump(signoz): de93bd31 → 0a516863 ↗ anthropics/knowledge-work-plugins
  10. [10] bump(carta-crm): 62e9f9a0 → f57875b3 ↗ anthropics/claude-plugins-official
  11. [11] bump(hyperframes): 5bfda4e0 → 2dddb4c4 ↗ anthropics/claude-plugins-official
  12. [12] bump(remember): 9bf9939d → 49978764 ↗ anthropics/claude-plugins-official
  13. [13] bump(wix): ca13a745 → 87c6b285 ↗ anthropics/claude-plugins-official
  14. [14] bump(hyperframes): a0697306 → 5bfda4e0 ↗ 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 July 27, 2026?
Automated SHA bumps for 14 plugins passed validation overnight across the official, community, and knowledge-work plugin repos, with every PR validated before merge. In total, 43 pull requests landed.
Who contributed to Anthropic on July 27, 2026?
1 developer shipped this update, including github-actions.
What were the notable Anthropic updates?
bump(adcp-client): 3d7b4b2a → e0562580, bump(ai-coding-ok): 1f9d3eed → c96068cd, and bump(ai-devkit): 116c3bb4 → 15b09d2d.
♥

$ 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.