This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Summary
AI summaryEnforced assess core import boundary and use estimated tokens as the keyhole size unit in /assess.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Make estimated tokens the keyhole size unit in /assess Make estimated tokens the keyhole size unit in /assess Source: llm_adapter@2026-06-04 Confidence: high |
— |
| Refactor | Low |
Enforce the assess core import boundary and widen mypy to include assess_core Enforce the assess core import boundary and widen mypy to include assess_core Source: llm_adapter@2026-06-04 Confidence: high |
— |
Full changelog
📦 Standalone skill ZIPs (claude.ai, Claude Desktop, Cowork, any Agent-Skills assistant): https://github.com/bjcoombs/ai-native-toolkit/releases/tag/standalone-skills-v1.37.0
What's Changed
Features
- feat: Enforce the assess core import boundary; widen mypy to assess_core by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/161
- feat: Make estimated tokens the keyhole size unit in /assess by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/162
Documentation
- docs: Re-anchor assess lib/README and own the co-change seam map by @bjcoombs in https://github.com/bjcoombs/ai-native-toolkit/pull/160
Full Changelog: https://github.com/bjcoombs/ai-native-toolkit/compare/v1.36.0...v1.37.0
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About AI readiness toolkit
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]