MindPatternSubscribe

Source trail

Marmelab: The State Of AI Harness Engineering 2026

Public MindPattern findings, entities, and graph evidence that cite this source.

Findings

1

All-time hits

1

High value

0

Last seen

2026-09-26

Related findings

2026-09-26 / SKILLSAudit of 246 agent-harness repos found only 4.4% of security rules in public .claude/ files have an enforcement mechanismFrançois Zaninotto's 24 Sep audit of 246 open-source harness repos and 57 publications found that 60% of the harnesses have neither tests nor evals, and that only 4.4% of the security rules written in public .claude/ directories are backed by an executable guard. It collects cited results that the same model scored 68-88% across eight harnesses, that machine-generated context files lowered success while human-written ones added about 4%, and that Vercel's agent went from 80% to 100% success on half the tokens after dropping 80% of its tools. Its main recommendation is to turn every prose rule that matters into a hook or script and to keep a decision record with an expiry condition for each control.

Open latest cited source