H
Howardism
Howardism · Vol. 03Plate I · No. 01

Harness, tagged.

Notes29TagHarnessOldest6 May 2026Newest25 Sept 2026

Every article tagged harness, newest first.

  1. C01
    Harness Tax: Coding-Agent Cost Multiplies Across Harnesses While Success Barely Moves
    BenchmarksHarnessCoding Agents+3
    · 10′
  2. C02
    Human-Governed Skill Maintenance
    AI Coding WorkflowAgent EngineeringHarness+2
    · 26′
  3. C03
    Harness Activation and Adherence
    Agent EngineeringHarnessSkills+2
    · 30′
  4. S04
    Harness Value Is a Product, Not a Score — Why the Artifact-Payoff Questions Keep Returning Partially Answered
    DerivedHarnessAgent Engineering+2
    · 14′
  5. C05
    Agentic Code Generation as Compilation
    Agent EngineeringHarnessDeterminism+2
    · 14′
  6. C06
    Deterministic Engineering for Agent Code Review
    Agent EngineeringCode ReviewHarness+3
    · 42′
  7. C07
    Continuous Self-Modification Under Review
    Recursive Self ImprovementHarnessAgent Engineering+2
    · 28′
  8. C08
    User Awareness
    AlignmentSafetyEvaluation+2
    · 34′
  9. S09
    Authority and Audit Survive Abundance
    DerivedHarnessAuthorization+2
    · 12′
  10. C10
    Harness-Induced Belief Divergence
    Agent EngineeringHarnessEvaluation+2
    · 21′
  11. S11
    What Makes a Self-Improvement Artifact Transfer?
    DerivedAgent EngineeringHarness+2
    · 14′
  12. C12
    Agent-Authored Harness Optimization
    Agent EngineeringHarnessEvaluation+2
    · 127′
  13. E13
    Cline
    EntityAgent RuntimeCoding Agent+2
    · 12′
  14. C14
    Deterministic Pre-Execution Gates
    Agent EngineeringHarnessFailure Modes+2
    · 39′
  15. C15
    Harness Build-vs-Buy
    Agent EngineeringHarnessTechnical Debt+2
    · 20′
  16. C16
    Layerwise Omission Attribution
    Agent EngineeringFailure ModesContext Management+2
    · 26′
  17. C17
    Orchestration Sets Token Economics
    Agent EngineeringHarnessCost+2
    · 34′
  18. C18
    Shared Harness, Differentiated Surfaces
    Agent EngineeringHarnessProduct Architecture+1
    · 12′
  19. S19
    Verifying Without a Compiler: Cowork's Harness vs Claude Code's, and Why the Slice Verifier Stays
    DerivedVerificationCowork+2
    · 6′
  20. S20
    What Scaffolding Survives Model Improvement — and How Do You Know When a Line Turns Harmful?
    DerivedHarnessAgent Engineering+2
    · 9′
  21. C21
    Instruction Compounding
    Agent EngineeringHarnessPrompting+1
    · 24′
  22. C22
    Output Length Calibration
    Agent EngineeringHarnessPrompting+1
    · 8′
  23. C23
    Agentic Work Systematization
    Agent EngineeringHarnessAutomation+4
    · 28′
  24. C24
    Loop Engineering
    Agent EngineeringHarnessAutomation+1
    · 32′
  25. S25
    Where Does Agent Harness Work Remain Durable as Models Improve?
    HarnessAgent EngineeringVerification+1
    · 9′
  26. C26
    Agent Context Files
    Agent EngineeringHarnessWorkflow Design+1
    · 96′
  27. S27
    Does the Human-Facing Harness (HTML Artifacts) Hit Its Own Bloat Ceiling?
    HarnessHuman AI CollaborationAgent Engineering+1
    · 6′
  28. C28
    Agent Loop Pattern
    Agent EngineeringHarnessAutomation
    · 11′
  29. C29
    Harness Shrinkage as Models Improve
    LLM ArchitectureAgent EngineeringHarness
    · 51′