plaited/agent-eval-harness

1

agent-eval-harness CLI tool for capturing agent trajectories. Execute prompts against headless CLI agents via schema-driven adapters, ca…

plaited/agent-eval-harness

19

2

validate-skill Validate skill directories against AgentSkills spec

plaited/agent-eval-harness

12

3

headless-adapters Discover, create, and validate headless adapters for agent integration. Includes scaffolding tools and schema-driven …

plaited/agent-eval-harness

11

4

optimize-agents-md Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, co…

plaited/agent-eval-harness

10

5

code-documentation TSDoc standards for TypeScript/JavaScript code. Automatically invoked when writing, reviewing, or editing any TSDoc c…

plaited/agent-eval-harness

9

6

typescript-lsp Search TypeScript SYMBOLS (functions, types, classes) - NOT text. Use Glob to find files, Grep for text search, LSP f…

plaited/agent-eval-harness

9

7

scaffold-rules Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventio…

plaited/agent-eval-harness

8

8

grill-me Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of …

plaited/agent-eval-harness

2

9

trial-runner End-to-end eval-suite orchestration with the `eval` command: run -> grade -> compare -> calibrate, using strict JSON …

plaited/agent-eval-harness

2

10

compare-trials Analyze graded `trial_result` JSONL outputs from the eval pipeline, including reliability and custom slicing.

plaited/agent-eval-harness

1

11

tdd Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first…

plaited/agent-eval-harness

1

12

trial-adapters Build command-only adapters for `eval` run mode using strict stdin/stdout JSON contracts.

plaited/agent-eval-harness

1