v0.11.0

What's Changed

• docs(landing): rewrite around slim + real measured numbers by @benlamlih in #58
• docs(readme): two-minute slim start before the full quickstart by @benlamlih in #59
• docs(landing): adopt the Claude-design page by @benlamlih in #60
• fix(landing): ship the design comp verbatim with its runtime by @benlamlih in #61
• ci+docs: macOS in the CI matrix; platform statement; curation.md to slim v2 by @benlamlih in #62
• feat(report): adopt the designed honesty-layer report by @benlamlih in #63
• chore(release): v0.11.0 by @benlamlih in #64

Full Changelog: v0.10.1...v0.11.0

v0.10.1

What's Changed

• fix(slim): audit plugins-only configs; read both plugin .mcp.json shapes by @benlamlih in #56
• chore(release): v0.10.1 by @benlamlih in #57

Full Changelog: v0.10.0...v0.10.1

v0.10.0

What's Changed

• feat(slim): dedupe v2 — cluster consolidation and drop fully-hidden servers by @benlamlih in #50
• feat(slim): tool-search-aware audit and alwaysLoad recommendations by @benlamlih in #51
• feat(slim): --share prints a copy-pasteable audit snippet by @benlamlih in #52
• docs: prove-your-gateway recipe + scale-and-proof README framing by @benlamlih in #53
• feat(slim): audit MCP servers shipped by Claude Code plugins by @benlamlih in #54
• chore(release): v0.10.0 by @benlamlih in #55

Full Changelog: v0.9.1...v0.10.0

v0.9.1

What's Changed

• fix(slim): five bugs from adversarial testing by @benlamlih in #48
• chore(release): v0.9.1 by @benlamlih in #49

Full Changelog: v0.9.0...v0.9.1

v0.9.0

What's Changed

• feat(slim): audit and shrink an MCP client config's union tool surface by @benlamlih in #46
• chore(release): v0.9.0 by @benlamlih in #47

Full Changelog: v0.8.0...v0.9.0

v0.8.0

What's Changed

• fix: measurement-correctness and robustness fixes (top 5 review findings) by @benlamlih in #32
• fix: measurement hardening — variance, timeouts, injection delimiting, validation by @benlamlih in #33
• fix: trustworthy CLI — user-test bug fixes, opt-in telemetry, v0.7.0 by @benlamlih in #34
• chore: OSS hygiene pack — contributing, templates, Dependabot, badges by @benlamlih in #35
• chore(deps): bump actions/checkout from 5 to 7 by @dependabot[bot] in #40
• chore(deps): bump actions/configure-pages from 5 to 6 by @dependabot[bot] in #41
• chore(deps): bump actions/upload-artifact from 4 to 7 by @dependabot[bot] in #39
• chore(deps): bump actions/download-artifact from 4 to 8 by @dependabot[bot] in #37
• chore(deps): bump actions/upload-pages-artifact from 3 to 5 by @dependabot[bot] in #36
• chore(deps): bump openai from 2.44.0 to 2.45.0 by @dependabot[bot] in #38
• chore(deps-dev): bump ruff from 0.15.20 to 0.15.21 by @dependabot[bot] in #42
• chore(deps-dev): update uv-build requirement from <0.9.0,>=0.8.17 to >=0.8.17,<0.12.0 by @dependabot[bot] in #43
• feat(scoring): flag hit-rate improvements within run-to-run noise by @benlamlih in #44
• chore(release): v0.8.0 by @benlamlih in #45

New Contributors

• @dependabot[bot] made their first contribution in #40

Full Changelog: v0.6.0...v0.8.0

v0.6.0

What's Changed

• feat(scoring): failures are loud in summaries by @benlamlih in #29
• docs(readme): document everything shipped since v0.2.0 by @benlamlih in #30
• chore(release): v0.6.0 by @benlamlih in #31

Full Changelog: v0.5.0...v0.6.0

v0.5.0

What's Changed

• feat(plan-init): --from-traces keeps what real runs actually called by @benlamlih in #25
• feat(generate): steer criteria away from volatile facts on live sources by @benlamlih in #26
• feat(run): --concurrency runs independent tasks in parallel by @benlamlih in #27
• chore(release): v0.5.0 by @benlamlih in #28

Full Changelog: v0.4.0...v0.5.0

v0.4.0

What's Changed

• feat(cli): plan-init scaffolds a keep-these-hide-the-rest view plan by @benlamlih in #21
• feat(curate): --prune-unused hides tools the eval never touched by @benlamlih in #22
• feat(cli): 'whetkit fix' — self-correcting curation by @benlamlih in #23
• chore(release): v0.4.0 by @benlamlih in #24

Full Changelog: v0.3.0...v0.4.0

v0.3.0

What's Changed

• fix(cli): friendly error when --server can't be resolved by @benlamlih in #13
• feat(mcp): ${VAR} expansion in server.json by @benlamlih in #14
• feat(scoring): flag probable task-spec gaps by @benlamlih in #15
• feat(generate): server execution context and read-only default by @benlamlih in #16
• feat(cli): 'whetkit diff' compares two summary-json files by @benlamlih in #18
• feat(llm): rough USD cost estimates next to token counts by @benlamlih in #19
• feat(run): --reset-cmd resets stateful fixtures between repetitions by @benlamlih in #17
• chore(release): v0.3.0 by @benlamlih in #20

Full Changelog: v0.2.0...v0.3.0