Original
Execution Profile Audit
Compare an intended agent execution profile with current worktree-bound observations, separating requested settings, resolved configuration, and actual runtime behavior.
Harness engineeringexperimental
← All bundles
12 CANONICAL SKILLS · V0.1.1
Harness Engineering and Qualification
Audit execution, revalidate context, reconcile readiness and usage, qualify controller failures, and review bounded canaries without another scheduler.
Inspect the selection
View manifest ↗Run from a full toolkit checkout. This prints a file manifest, not an installer.
node tools/bundle.mjs resolve harness-engineeringOriginal
Agent Runtime Adapter Qualification
Qualify one controller-to-agent execution interface for lifecycle, event identity, cancellation, authentication, and uncertain outcomes before admitting real tasks.
Harness engineeringexperimental
Original
Tracker Readiness Reconciliation
Reconcile full task identity, accepted prerequisites, source contracts, and ownership immediately before dispatch without treating labels or filtered queries as acceptance.
Harness engineeringexperimental
Original
Controller Conformance Testing
Test a selected controller against deterministic readiness, restart, cancellation, retention, stale-attempt, and independent-acceptance scenarios before deployment.
Harness engineeringexperimental
Original
Agent Event and Usage Reconciliation
Normalize runtime event captures with explicit identity, usage basis, duplicate handling, missing coverage and independent acceptance boundaries.
Harness engineeringexperimental
Original
Tested Structural Refactoring
Author and qualify scoped structural transformations with positive and negative examples, reviewed diffs, repeat-application checks, and independent runtime/type validation.
Structural editingexperimental
Original
Context Checkpointing
Preserve task state across compaction or handoff with source-backed decisions, unresolved failures, current artifacts, and explicit freshness checks.
Context and memoryexperimental
Original
Subagent Lifecycle
Track allocated, running, submitted, accepted, failed, and indeterminate work with explicit ownership and recoverable interruption.
Agent orchestrationexperimental
Original
Orchestration Resume
Resume interrupted coordination from checked run records, reusing only current accepted artifacts and withholding ambiguous or stale work.
Agent orchestrationexperimental
Original
Agent Loop Detection
Detect repeated no-progress tool calls, equivalent patches, and unchanged failures using bounded evidence windows and explicit stop/escalation criteria.
Agent runtimeexperimental
Original
Delegation Evaluation
Evaluate whether delegation improves accepted task outcomes using matched inputs, independent checks, repeated sessions, and explicit handoff/integration scoring.
Testingexperimental
Original
Bounded Harness Canary
Evaluate one harness change with a fixed workload, explicit limits, all-attempt accounting, independent integration evidence, and a review decision that preserves unfinished work.
Harness engineeringexperimental
Tailor context, not a second copy.
Pick the skill needed for the current task. A private adapter supplies project-specific roots, command IDs, accepted contracts, and policy. It should pin and verify the public revision before exposing guidance to an internal agent.
Skill effectiveness remains experimental. Package validation and content hashes do not establish host compatibility, artifact authenticity, or permission to execute.
Read the private-adapter boundary ↗