@mutagent/evaluator 0.1.0-alpha.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude/skills/mutagent-evaluator/SKILL.md +538 -0
- package/.claude/skills/mutagent-evaluator/assets/agents/audit-executor.md +169 -0
- package/.claude/skills/mutagent-evaluator/assets/agents/dataset-builder.md +160 -0
- package/.claude/skills/mutagent-evaluator/assets/agents/discovery.md +425 -0
- package/.claude/skills/mutagent-evaluator/assets/agents/evaluator.md +1044 -0
- package/.claude/skills/mutagent-evaluator/assets/brand/theme.css +213 -0
- package/.claude/skills/mutagent-evaluator/assets/brand/wordmark.html +9 -0
- package/.claude/skills/mutagent-evaluator/lenses/context-flow-lens.md +85 -0
- package/.claude/skills/mutagent-evaluator/lenses/data-lens.md +47 -0
- package/.claude/skills/mutagent-evaluator/lenses/decision-lens.md +48 -0
- package/.claude/skills/mutagent-evaluator/lenses/methodology-critic-lens.md +53 -0
- package/.claude/skills/mutagent-evaluator/lenses/trajectory-lens.md +44 -0
- package/.claude/skills/mutagent-evaluator/references/build-review-interface.md +83 -0
- package/.claude/skills/mutagent-evaluator/references/edd-loop.md +134 -0
- package/.claude/skills/mutagent-evaluator/references/error-analysis.md +113 -0
- package/.claude/skills/mutagent-evaluator/references/eval-audit.md +154 -0
- package/.claude/skills/mutagent-evaluator/references/eval-stage.md +168 -0
- package/.claude/skills/mutagent-evaluator/references/generate-synthetic-data.md +81 -0
- package/.claude/skills/mutagent-evaluator/references/grounded-adjudication.md +221 -0
- package/.claude/skills/mutagent-evaluator/references/memory-format.md +65 -0
- package/.claude/skills/mutagent-evaluator/references/methodology.md +201 -0
- package/.claude/skills/mutagent-evaluator/references/operation-inventory.md +196 -0
- package/.claude/skills/mutagent-evaluator/references/validate-evaluator.md +125 -0
- package/.claude/skills/mutagent-evaluator/references/workflows/orchestrator-protocol.md +287 -0
- package/.claude/skills/mutagent-evaluator/references/write-judge-prompt.md +123 -0
- package/.claude/skills/mutagent-evaluator/schemas/behavior-tree.schema.yaml +73 -0
- package/.claude/skills/mutagent-evaluator/schemas/dataset.schema.yaml +66 -0
- package/.claude/skills/mutagent-evaluator/schemas/edd-change-request.schema.yaml +114 -0
- package/.claude/skills/mutagent-evaluator/schemas/eval-matrix.schema.yaml +74 -0
- package/.claude/skills/mutagent-evaluator/schemas/flow-graph.schema.yaml +69 -0
- package/.claude/skills/mutagent-evaluator/schemas/flow-profile.schema.yaml +49 -0
- package/.claude/skills/mutagent-evaluator/schemas/methodology-review.schema.yaml +40 -0
- package/.claude/skills/mutagent-evaluator/schemas/scorecard.schema.yaml +85 -0
- package/.claude/skills/mutagent-evaluator/scripts/agent-dispatch.ts +0 -0
- package/.claude/skills/mutagent-evaluator/scripts/aggregate-discover.ts +543 -0
- package/.claude/skills/mutagent-evaluator/scripts/artifact-paths.ts +99 -0
- package/.claude/skills/mutagent-evaluator/scripts/assemble-scorecard.ts +172 -0
- package/.claude/skills/mutagent-evaluator/scripts/build-dataset.ts +186 -0
- package/.claude/skills/mutagent-evaluator/scripts/build-evals.ts +93 -0
- package/.claude/skills/mutagent-evaluator/scripts/build-review-ui.ts +393 -0
- package/.claude/skills/mutagent-evaluator/scripts/check-method-router.ts +170 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/aggregate.ts +112 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/audit-run.ts +175 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/doctor.ts +211 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/dogfood.ts +133 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/init.ts +601 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/methodology-review.ts +122 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/prep.ts +279 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/profile-subject.ts +165 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/run.sh +56 -0
- package/.claude/skills/mutagent-evaluator/scripts/cli/variance-check.ts +105 -0
- package/.claude/skills/mutagent-evaluator/scripts/code-eval.ts +248 -0
- package/.claude/skills/mutagent-evaluator/scripts/codegen-evals.ts +173 -0
- package/.claude/skills/mutagent-evaluator/scripts/cold-start-project.ts +151 -0
- package/.claude/skills/mutagent-evaluator/scripts/cold-start-sampler.ts +267 -0
- package/.claude/skills/mutagent-evaluator/scripts/config/load.ts +307 -0
- package/.claude/skills/mutagent-evaluator/scripts/config/schema.ts +325 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/agentspec-evals.ts +85 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/dataset.ts +149 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/eval-engine.ts +118 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/eval-matrix.ts +577 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/eval-types.ts +1074 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/flow-graph.ts +194 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/types.ts +303 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/validation.ts +193 -0
- package/.claude/skills/mutagent-evaluator/scripts/derive-dataset.ts +152 -0
- package/.claude/skills/mutagent-evaluator/scripts/determine-outcome.ts +219 -0
- package/.claude/skills/mutagent-evaluator/scripts/diff-discriminate.ts +160 -0
- package/.claude/skills/mutagent-evaluator/scripts/discover-criteria.ts +348 -0
- package/.claude/skills/mutagent-evaluator/scripts/edd/change-request.ts +232 -0
- package/.claude/skills/mutagent-evaluator/scripts/edd/edd-types.ts +210 -0
- package/.claude/skills/mutagent-evaluator/scripts/edd/variance-gate.ts +186 -0
- package/.claude/skills/mutagent-evaluator/scripts/emit-completeness.ts +111 -0
- package/.claude/skills/mutagent-evaluator/scripts/eval-engine.ts +160 -0
- package/.claude/skills/mutagent-evaluator/scripts/evaluate.ts +333 -0
- package/.claude/skills/mutagent-evaluator/scripts/flow-graph.ts +230 -0
- package/.claude/skills/mutagent-evaluator/scripts/judge-prompt-template.ts +253 -0
- package/.claude/skills/mutagent-evaluator/scripts/judge-provider.ts +135 -0
- package/.claude/skills/mutagent-evaluator/scripts/lint-grounding.ts +229 -0
- package/.claude/skills/mutagent-evaluator/scripts/lint-uniformity.ts +168 -0
- package/.claude/skills/mutagent-evaluator/scripts/living-suite.ts +109 -0
- package/.claude/skills/mutagent-evaluator/scripts/load-bundle.ts +203 -0
- package/.claude/skills/mutagent-evaluator/scripts/load-profile-vocab.ts +64 -0
- package/.claude/skills/mutagent-evaluator/scripts/load-profile.ts +106 -0
- package/.claude/skills/mutagent-evaluator/scripts/mask.ts +138 -0
- package/.claude/skills/mutagent-evaluator/scripts/materialize-dataset.ts +113 -0
- package/.claude/skills/mutagent-evaluator/scripts/matrix-judge.ts +750 -0
- package/.claude/skills/mutagent-evaluator/scripts/memory/append.ts +215 -0
- package/.claude/skills/mutagent-evaluator/scripts/memory/read.ts +168 -0
- package/.claude/skills/mutagent-evaluator/scripts/prep-tasks.ts +125 -0
- package/.claude/skills/mutagent-evaluator/scripts/profile-subject.ts +310 -0
- package/.claude/skills/mutagent-evaluator/scripts/publish-report.ts +131 -0
- package/.claude/skills/mutagent-evaluator/scripts/read-unitf-traces.ts +81 -0
- package/.claude/skills/mutagent-evaluator/scripts/render-build-cards.ts +195 -0
- package/.claude/skills/mutagent-evaluator/scripts/render-discover-report.ts +1640 -0
- package/.claude/skills/mutagent-evaluator/scripts/render-eval-report.ts +3823 -0
- package/.claude/skills/mutagent-evaluator/scripts/render-report.ts +212 -0
- package/.claude/skills/mutagent-evaluator/scripts/resolve-credential.ts +110 -0
- package/.claude/skills/mutagent-evaluator/scripts/resolve-ref.ts +98 -0
- package/.claude/skills/mutagent-evaluator/scripts/result-verify.ts +129 -0
- package/.claude/skills/mutagent-evaluator/scripts/route-failures.ts +320 -0
- package/.claude/skills/mutagent-evaluator/scripts/run-deterministic.ts +271 -0
- package/.claude/skills/mutagent-evaluator/scripts/run-evaluate.ts +715 -0
- package/.claude/skills/mutagent-evaluator/scripts/run-judge.ts +155 -0
- package/.claude/skills/mutagent-evaluator/scripts/run-pipeline.ts +175 -0
- package/.claude/skills/mutagent-evaluator/scripts/sample-traces.ts +210 -0
- package/.claude/skills/mutagent-evaluator/scripts/self-audit.ts +387 -0
- package/.claude/skills/mutagent-evaluator/scripts/source-map.ts +106 -0
- package/.claude/skills/mutagent-evaluator/scripts/subject-profile.ts +134 -0
- package/.claude/skills/mutagent-evaluator/scripts/substrate.ts +162 -0
- package/.claude/skills/mutagent-evaluator/scripts/ui-slots.ts +119 -0
- package/.claude/skills/mutagent-evaluator/scripts/unitf-to-evaltrace.ts +284 -0
- package/.claude/skills/mutagent-evaluator/scripts/validate-judge.ts +358 -0
- package/.claude/skills/mutagent-evaluator/scripts/variance-compare.ts +177 -0
- package/.claude/skills/mutagent-evaluator/subjects/mutagent-diagnostics/behavior-tree.yaml +140 -0
- package/.claude/skills/mutagent-evaluator/subjects/mutagent-diagnostics/eval-matrix.yaml +1270 -0
- package/.claude/skills/mutagent-evaluator/subjects/mutagent-diagnostics/methodology-review.yaml +105 -0
- package/.claude/skills/mutagent-evaluator/workflows/audit.workflow.js +82 -0
- package/.claude/skills/mutagent-evaluator/workflows/data-leak.workflow.js +236 -0
- package/.claude/skills/mutagent-evaluator/workflows/variance.workflow.js +163 -0
- package/LICENSE +201 -0
- package/NOTICE +23 -0
- package/README.md +90 -0
- package/bin/mutagent-cli.mjs +9263 -0
- package/bin/mutagent-evaluator.mjs +96 -0
- package/package.json +52 -0
There are too many changes on this page to be displayed.
The amount of changes on this page would crash your brower.
You can still verify the content by downloading the package file manually.