Intense-Visions

Intense-Visions/harness-engineering

Agent

Constructs failure scenarios between the existing 4 review agents — assumption violations, composition failures, abuse cases, and cascade chains.

Intense-Visions/harness-engineering

Agent

Validate architectural constraints and dependency rules. Use when checking layer boundaries, detecting circular dependencies, or verifying import direction compliance.

Intense-Visions/harness-engineering

Agent

Perform code review and address review findings using harness methodology. Use when reviewing code, fixing review findings, responding to review feedback, or when a code review has produced issues that need to be addressed.

Intense-Visions/harness-engineering

Agent

Proactively identifies structural problems, coupling risks, and architectural drift.

Intense-Visions/harness-engineering

Agent

Keep documentation in sync with source code. Use when detecting documentation drift, validating doc coverage, or aligning docs with code changes.

Intense-Visions/harness-engineering

Agent

Detect and fix codebase entropy including drift, dead code, and pattern violations. Use when running cleanup, detecting dead code, or fixing pattern violations.

Intense-Visions/harness-engineering

Agent

Framework-aware reviewer for async-UI diffs — flags lifecycle gaps, hook-timing mistakes, concurrent interactions, and stale-work races.

Intense-Visions/harness-engineering

Agent

Keeps the knowledge graph fresh, monitors connector health, and ensures data quality.

Intense-Visions/harness-engineering

Agent

Owns acceptance-criteria and eval-coverage quality for specs.

Intense-Visions/harness-engineering

Agent

Dispatch independent tasks across isolated agents for parallel execution. Use when multiple independent tasks need to run concurrently, splitting work across agents, or coordinating parallel implementation.

Intense-Visions/harness-engineering

Agent

Enforces performance budgets and detects regressions.

Intense-Visions/harness-engineering

Agent

Create detailed implementation plans from specs with task breakdown, dependency ordering, and checkpoint placement. Use when planning a phase, breaking a spec into tasks, or creating an execution plan.

Intense-Visions/harness-engineering

Agent

Security-focused code reviewer with OWASP/CWE expertise.

Intense-Visions/harness-engineering

Agent

Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.

Intense-Visions/harness-engineering

Agent

Framework-aware reviewer for TypeScript diffs — flags type holes, refactor regressions, complexity growth, and five-second-rule names.

Intense-Visions/harness-engineering

Agent

Verify implementation completeness against spec and plan at three tiers (EXISTS, SUBSTANTIVE, WIRED). Use when checking if built code matches what was planned, validating phase completion, or auditing implementation quality.

Intense-Visions/harness-engineering

Command Claude Code

Pre-execution LLM-judgment skill: does a spec carry measurable, testable, complete acceptance criteria before work begins? Resolves the spec's acceptance section, critiques observability / testability / completeness (advisory), flags user-visible behaviors with no covering test (advisory), and emits a confidence-rated…

Intense-Visions/harness-engineering

Command Claude Code

Add a component to an existing harness project.

Intense-Visions/harness-engineering

Command Claude Code

Autonomous decide-stage orchestrator — sweep the backlog of pending architectural decisions, fan out worktree-isolated subagents that each run the real architecture-advisor pipeline to draft one ADR, independently verify every draft is a well-formed record, and hand the human one batch sign-off pass. Never…

Intense-Visions/harness-engineering

Command Claude Code

Apply codemods for safe DRIFT-T001/T002/T003 token-bypass findings; emit precise suggestions for DRIFT-T004 (deprecated tokens) and all DRIFT-P (primitive adoption). FIX half of the design-pipeline drift-remediation sub-project; pairs with detect-design-drift.

Intense-Visions/harness-engineering

Command Claude Code

LLM-judgment critique of API design quality — the ceiling counterpart to rule-based API checks (OpenAPI-format and webhook-format compliance). Asks whether resources model the domain rather than the implementation, whether resource naming and URL structure are predictable (path vs query param), whether HTTP methods…

Intense-Visions/harness-engineering

Command Claude Code

Interactive architecture advisor that surfaces trade-offs and helps humans choose.

Intense-Visions/harness-engineering

Command Claude Code

Rule-based brand-semantics audit. Detects token misuse (BRAND-T001 via $extensions.harness.brand.forbiddencontexts) and voice violations (BRAND-V001 via DESIGN.md voice.forbiddenphrases). 4th composed verifier in harness check-design. Triggers extraction of the formal verifier interface.

Intense-Visions/harness-engineering

Command Claude Code

Audit component definitions for missing required anatomy parts (slots, states, sizes) and detect missing-anatomy-component patterns (data without empty states, async without loading boundaries). First programmatic enforcer of component-anatomy rules.