SeongwoongCho

SeongwoongCho/adaptive-harness

Plugin Claude Code

Self-improving harness router and evaluator for Claude Code.

SeongwoongCho/adaptive-harness

Plugin Claude Code

A self-improving harness router and evaluator for Claude Code — automatically selects, evaluates, and evolves the right harness for your repo.

SeongwoongCho/adaptive-harness

Settings file Claude Code

Agent settings configuring env.

SeongwoongCho/adaptive-harness

Instructions file

Instructions for SeongwoongCho/adaptive-harness, covering adaptive-harness — project instructions for ai agents, git workflow, branch structure, rules for ai agents and release flow.

SeongwoongCho/adaptive-harness

Agent

Self-attacking implementation executor. Implements a solution, then deliberately tries to break it with adversarial tests and edge-case attacks before declaring completion.

SeongwoongCho/adaptive-harness

Agent

Safe refactoring specialist. Applies the Mikado method to restructure code without changing observable behavior.

SeongwoongCho/adaptive-harness

Agent

Multi-perspective code reviewer. Evaluates code across security, quality, performance, and maintainability dimensions.

SeongwoongCho/adaptive-harness

Agent

Clarification-first executor. Resolves ambiguous requirements through structured interviews, builds a confirmed spec, then executes against it.

SeongwoongCho/adaptive-harness

Agent

Decomposition executor. Splits large tasks into independent sub-tasks, solves each in isolation, then integrates and verifies the combined result.

SeongwoongCho/adaptive-harness

Agent

Documentation specialist. Reads source truth first, then drafts accurate and well-styled docs, READMEs, API references, and guides.

SeongwoongCho/adaptive-harness

Agent

Weekly engineering retrospective specialist. Analyzes commit history, work patterns, and contributor metrics with trend tracking and team-aware praise and growth coaching.

SeongwoongCho/adaptive-harness

Agent

Scores task results using 6 universal dimensions and collected evidence.

SeongwoongCho/adaptive-harness

Agent

Analyzes evaluation history and proposes harness modifications for next-session evolution.

SeongwoongCho/adaptive-harness

Agent

Safe migration specialist. Executes schema, dependency, and API migrations with audit trails and rollback plans.

SeongwoongCho/adaptive-harness

Agent

Task decomposition specialist. Analyzes a task, identifies independent sub-tasks, and emits a structured decomposition JSON that the orchestrator uses to fan out parallel execution.

SeongwoongCho/adaptive-harness

Agent

Performance optimizer. Establishes baselines, profiles bottlenecks, and applies measurement-driven optimizations one at a time.

SeongwoongCho/adaptive-harness

Agent

Engineering plan reviewer. Challenges scope, reviews architecture/quality/tests/performance one issue at a time, and produces a completion summary with failure mode analysis.

SeongwoongCho/adaptive-harness

Agent

Pre-merge diff reviewer. Analyzes the branch diff against main in two passes — Critical (blocking) and Informational (advisory) — and interactively resolves critical issues.

SeongwoongCho/adaptive-harness

Agent

Iterative quality improvement executor. Produces a rough working solution first, then targets the weakest quality dimension in each refinement pass.

SeongwoongCho/adaptive-harness

Agent

Systematic QA testing specialist. Tests applications like a real user, computes a health score, and produces a structured report with screenshot evidence and repro steps.

SeongwoongCho/adaptive-harness

Agent

Persistent execution loop. Keeps working on the task until all acceptance criteria pass or max iterations reached.

SeongwoongCho/adaptive-harness

Agent

Implementation planner with self-review. Analyzes requirements, explores the codebase, creates a structured plan, then challenges its own assumptions.

SeongwoongCho/adaptive-harness

Agent

Fast MVP builder. Implements the minimum viable version of a feature with speed as the primary constraint.

SeongwoongCho/adaptive-harness

Agent

Experimental research executor. Runs hypothesis-driven cycles to explore high-uncertainty problems with rigorous measurement.