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 2026-07-26
stories 47
GitHub RSS Archive Reviews

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

PLUGIN ECOSYSTEM SHIPS 47 VALIDATED UPDATES ACROSS THREE REPOS

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

github-actions
1 person shipped this
github-actions @github-actions 12 cited

Automated validation swept through the plugin ecosystem overnight, pushing 12 coordinated SHA bumps across community, official, and knowledge-work registries.

The community plugins repo saw five fresh SHAs validated and staged [1][2][3][4][5], touching sap-dev-core, adcp-client, agented, agentforce-adlc, and agentiqa. Knowledge-work-plugins queued carta-investors and auth0 updates [6][7], while the official registry absorbed cascading bumps across remember, hyperframes, carta-investors, and auth0 [8][9][10][11][12]. The carta-investors plugin is now two versions ahead in the official repo compared to knowledge-work, suggesting upstream changes propagating downstream. All 12 PRs passed `claude plugin validate` before automation opened them, but none auto-merged by default; each requires manual review before landing. The 47 PRs across the ecosystem represent the daily plugin refresh cycle operating at full velocity.

Action items

References

  1. [1] bump(sap-dev-core): cc5c7ddc → c1cf4a04 ↗ anthropics/claude-plugins-community
  2. [2] bump(adcp-client): cf08f7a6 → 3d7b4b2a ↗ anthropics/claude-plugins-community
  3. [3] bump(agented): 63443471 → 09d9429c ↗ anthropics/claude-plugins-community
  4. [4] bump(agentforce-adlc): 3d70dc3e → 74e7c25b ↗ anthropics/claude-plugins-community
  5. [5] bump(agentiqa): 5f148575 → 25e06848 ↗ anthropics/claude-plugins-community
  6. [6] bump(carta-investors): 485aee6b → 0ee76454 ↗ anthropics/knowledge-work-plugins
  7. [7] bump(auth0): e295fd64 → e6ffc31f ↗ anthropics/knowledge-work-plugins
  8. [8] bump(remember): e432107b → 1bf23171 ↗ anthropics/claude-plugins-official
  9. [9] bump(hyperframes): 3b3d4f55 → f9f00b0e ↗ anthropics/claude-plugins-official
  10. [10] bump(carta-investors): 0ee76454 → 5236d61b ↗ anthropics/claude-plugins-official
  11. [11] bump(hyperframes): 1f9a8f09 → 3b3d4f55 ↗ anthropics/claude-plugins-official
  12. [12] bump(auth0): e295fd64 → e6ffc31f ↗ 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 26, 2026?
Automated validation swept through the plugin ecosystem overnight, pushing 12 coordinated SHA bumps across community, official, and knowledge-work registries. In total, 47 pull requests landed.
Who contributed to Anthropic on July 26, 2026?
1 developer shipped this update, including github-actions.
What were the notable Anthropic updates?
bump(sap-dev-core): cc5c7ddc → c1cf4a04, bump(adcp-client): cf08f7a6 → 3d7b4b2a, and bump(agented): 63443471 → 09d9429c.
♥

$ 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.