harness-engineering 37
- OpenShell's auto-approval sees new methods, not wider paths
- Cloudflare OS simulates approvals, but never for MCP writes
- TypeSafe's routing verdict hinges on the price ratio
- GameDevBench's 68.8% top score is the only strictly confined row
- Orca's privacy page survives 82 of its 83 telemetry events
- Moli's efficiency map blends two runs its own bench keeps apart
- CodeBurn's $15 hard cap denies tools when it could stop Claude
- SoL-Pi's Capability Floor Is Per Mechanism, Not Per Harness
- TradingAgents and LibreChat Are Not Drop-In Replacements
- ripwire Guards Its Gate Count in Source, Not in the PDF
- Gensee Crate's Defense Rate Is the One Number You Cannot Recount
- MetaHarness Advertises Witness Signing Its Bridges Never Export
- HyperFrames Measures 'Same Video' in Decibels, Not Bytes
- SkillHub's Security Scanner Blocks on Crash, Not on Verdict
- CAO's Honest Trust Boundary and Its Phantom Auth Switch
- Ouroboros Preaches Agency and Ships Owner-First Custody
- Open Science's Provenance Engine Would Reject Its Own #1 Badge
- Apache Maka Tracks Its Agents' Screenshots and Ships None of Them
- OpenHarness Lets Its Allow List Outrank Your Deny Rules
- diagram-design Hash-Locks Its Screenshots, Not Its Storefront
- ECC Retired Six MCP Servers Over a Tax Its Catalog Still Pays
- OpenMAIC Source Audit: The Agent Classroom Ships Pedagogy as Machine-Checked Constraint Files
- Archify Source Audit: The Viral Diagram Skill Is Really a Distrust Stack
- One Memory Setup, Every Harness: Reading Omnigent's Hindsight Bridge at the Seam
- CLI-Anything Architecture: Why Agent-Native Interfaces Outweigh Model Scaling
- AutoBE Release Diff: 133 of 134 Compiler Files Match
- Engineering Discipline's handoff contradicts its gate
- Claude Code rewind depends on who changed the file
- Designing AI Agent Teams with Codex Subagents: A Practical Guide to Multi-Agent Workflows
- pi as the Core: Building Hackable Coding Agent Harnesses with TypeScript Extensions
- Harness Engineering: What a Benchmark Score Actually Measures
- The Agent SDK Landscape: Comparing Orchestration Runtimes and Harness Primitives
- Harness Engineering: Architectural Principles for Scaling Agents to 1M Lines
- Stop Generating, Start Thinking: Cognitive Debt and Verification in AI Engineering
- How Claude Code Works: The Agent Loop, Tool Dispatch, and Security Boundaries
- Towards Self-Driving Codebases: Architectural Lessons from Cursor's Agent Harness
- Claude Opus 4.6 and Agent Teams: Lessons from the 16-Agent Compiler Harness