harness-os

Rules and strategies for managing agent context window size, avoiding bloat, and preserving signal-to-noise ratio.

Standard patterns for error handling, retry logic, circuit breakers, and graceful degradation.

Detect and remove contradictions across agent policies before execution.

Multi-step tool workflows via code orchestration to reduce latency, context pollution, and token overhead.

Bind project-specific prompts to local schema and workflow artifacts while keeping the harness core generic and globally reusable.

Operational session protocol for task-scoped leases, reconciliation, checkpoints, inspection, queue promotion, and handoff across long-running work.

Operational session protocol for task-scoped leases, reconciliation, checkpoints, inspection, queue promotion, and handoff across long-running work.

Two-phase agent harness lifecycle — initializer session for scaffolding and incremental sessions for feature-by-feature execution with cross-session memory.

Execution plan with milestone/issue hierarchy, explicit dependencies, and safe parallelism.

Structured decision process between Non-Breaking and Breaking paths without relaxing quality gates.

Structured code review checklist covering correctness, security, performance, and maintainability.

Mandatory quality gate for every Issue, Milestone, and PR with zero-error execution and no technical debt carry-over.

Dependency audit, update policy, license verification, and supply chain security practices.

Deterministic, CI-ready end-to-end validation for critical user flows.

Branch naming, commit messages, PR conventions, and merge strategy for clean, traceable git history.

Keep local plan and GitHub project artifacts perfectly aligned with milestones, issues, labels, and statuses.

Iterative decision loop with consistent user checkpoints and explicit stop criteria.

Enforce the use of mcp_mobile_multi_action to reduce latency and improve reliability during Mobile MCP UI automation.

Structured performance audit covering Core Web Vitals, bundle size, memory profiling, and runtime efficiency.

Stop ineffective iteration loops and choose a controlled recovery path after repeated gate failures.

Accurate, auditable execution journal for each working session.

Evidence-based debugging via structured logging, debug-data.log analysis, and MCP tool integration — replaces trial-and-error.

Deterministic, CI-ready quality verification with no regressions and no coverage drop.

How to automatically configure, install, and sync HarnessOS to any host (Gemini, Cursor, Copilot, Windsurf) without human intervention.

Bind project-specific prompts to local schema and workflow artifacts while keeping the harness core generic and globally reusable.