Who contributed to Anthropic on May 13, 2026?

4 developers shipped this update, including morganl-ant, dicksontsai, markpikemarkpike, and tobinsouth.

What were the notable Anthropic updates?

code-modernization: fix pipeline gaps, redesign harden, dry-run hardening, Fix servicenow-sdk ref: ServiceNow/sdk uses master, not main, and Remove Lexis references at partner request.

@anthropics

Claude SDKs and developer tooling

github ↗

Pick a date

Topics: AI / ML Full archive →

The Wire · Showcase

CODE MODERNIZATION PIPELINE FIXED, LEXIS PURGED FROM LEGAL SUITE

By RepoJournal · Filed 06:02 UTC on May 13, 2026 · About Anthropic

4 people shipped this

markpikemarkpike @markpikemarkpike 2 cited

morganl-ant @morganl-ant 1 cited

dicksontsai @dicksontsai 1 cited

tobinsouth @tobinsouth 1 cited

The code-modernization plugin's discovery workflow is no longer dead-ending mid-pipeline, and Thomson Reuters just replaced LexisNexis as Anthropic's legal partner.

The modernize-brief-to-map handoff has been broken for weeks [1]. The brief step read TOPOLOGY.md but the map step writes to TOPOLOGY.html — a mismatch that killed the workflow cold. That's fixed now, along with a missing Priority field in the Rule Card that the P0 rules audit couldn't parse [1]. The ServiceNow SDK plugin was also pointing at a 'main' branch that doesn't exist; it's been corrected to 'master' where the pinned SHA actually lives [2]. Over in claude-for-legal, LexisNexis asked for a complete removal from connectors and examples across 97 files [3], while Thomson Reuters's CoCounsel Legal plugin is now live as a vendor-maintained partner integration under external_plugins/ [4]. The overnight QA re-run caught four critical findings in the legal suite: a silent data loss issue in renewal-register.yaml caching, broken /setup command references, a false-premise defense rule shipped to all 12 plugins instead of 1, and stale currency data [5]. These are all flagged for immediate merge.

Action items

→ Deploy code-modernization pipeline fixes before next discovery workflow run anthropics/claude-plugins-official [immediate]
→ Review and merge overnight QA fixes — four critical config and cache issues blocking legal suite anthropics/claude-for-legal [immediate]
→ Verify CoCounsel Legal MCP endpoint is live and OAuth tokens rotate correctly anthropics/claude-for-legal [plan]
→ Monitor Lexis removal didn't break any client integrations — was fully scoped to internal docs anthropics/claude-for-legal [monitor]

References

[1] code-modernization: fix pipeline gaps, redesign harden, dry-run hardening ↗ anthropics/claude-plugins-official
[2] Fix servicenow-sdk ref: ServiceNow/sdk uses master, not main ↗ anthropics/claude-plugins-official
[3] Remove Lexis references at partner request ↗ anthropics/claude-for-legal
[4] Add CoCounsel Legal partner plugin under external_plugins/ ↗ anthropics/claude-for-legal
[5] Launch morning fixes from overnight QA re-run ↗ anthropics/claude-for-legal

Quick answers

What shipped in Anthropic on May 13, 2026?: The code-modernization plugin's discovery workflow is no longer dead-ending mid-pipeline, and Thomson Reuters just replaced LexisNexis as Anthropic's legal partner. In total, 15 commits and 7 pull requests landed.
Who contributed to Anthropic on May 13, 2026?: 4 developers shipped this update, including morganl-ant, dicksontsai, markpikemarkpike, and tobinsouth.
What were the notable Anthropic updates?: code-modernization: fix pipeline gaps, redesign harden, dry-run hardening, Fix servicenow-sdk ref: ServiceNow/sdk uses master, not main, and Remove Lexis references at partner request.

CLAUDE AGENT SDK FIXES STDIN CLOSURE BUG IN BACKGROUND TASKS

The Python SDK's query method was prematurely closing stdin when background subagents were still in flight, breaking tool calls and silently bypassing hooks - now fixed in v0.2.127.

ai 16 shipped 1-min read

@anthropics 1 day ago

BUFFA v0.9.1 PATCHES REGRESSION THAT BROKE ORDINARY SCHEMAS

Buffa shipped an emergency patch overnight after v0.9.0 broke codegen on schemas with a few hundred proto files, small enough to hit in production.

ai 113 shipped 1-min read

@anthropics 2 days ago

CLAUDE FOUNDATION MODELS ADDS APP ATTEST, PLUGIN ECOSYSTEM STABILIZES

iOS developers can now ship Claude calls without API keys in the binary, backed by Apple's Secure Enclave.

ai 111 shipped 1-min read

@anthropics 3 days ago

BUFFA FIXES V0.9.0 REGRESSION, CLAUDE PLUGINS ECOSYSTEM GAINS 9 NEW INTEGRATIONS

Buffa's codegen was silently rejecting moderately large schemas due to a memory bound meant only for untrusted input, but a fix shipped overnight restores throughput and clears the path for googleapis-scale proto sets.

ai 156 shipped 2-min read

Elsewhere on the wire

AI Agents about 9 hours ago

CLAUDE OPUS 5 LANDS ACROSS THE STACK

The newest Anthropic model is now live in langchain, Cline, and llama-index, with native support for extended reasoning and 1M context windows.

ai-agents 28 shipped 1-min read

Local LLMs about 9 hours ago

OLLAMA LANDS LAGUNA SUPPORT AND CRUSHES MEMORY LEAKS WHILE SGLANG HITS V0.5.16 WITH CONFIDENCE-DRIVEN SPECULATIVE DECODING

Ollama shipped three critical performance and reliability fixes for Metal residency and concurrent access patterns, while SGL-Lang released 0.5.16 with a new speculative algorithm hitting 383.7 tok/s on DeepSeek-V4.