execute
01Command Claude Code
Implement the PLAN with continuous verification. Step 3 of the embedeval 5-stage workflow. Reports to screen only — no SESSION document.
Command Claude Code
Implement the PLAN with continuous verification. Step 3 of the embedeval 5-stage workflow. Reports to screen only — no SESSION document.
Command Claude Code
Analyze, design, and write a PLAN document. Step 2 of the embedeval 5-stage workflow. The PLAN file is the only persistent artifact in this workflow — /execute, /review, and /wrapup all report to screen only.
Command Claude Code
Sequentially author negatives.py for every case that lacks one, with interactive judgment gates where LLM cannot reliably decide.
Command Claude Code
Gather information, explore options, recommend an approach. Step 1 of the embedeval 5-stage workflow. Informs /myplan — does not create any file.
Command Claude Code
Deep review of task changes. Step 4 of the embedeval 5-stage workflow. Reports to screen only — no ANALYSIS document.
Command Claude Code
Run LLM benchmark, save detailed results, generate failure analysis report.
Command Claude Code
Final validation, docs sync, and commit. Step 5 of the embedeval 5-stage workflow. Reports to screen only — no WRAPUP/LEARNING document.
Instructions file
Instructions for Ecro/embedeval, covering embedeval, project context, tech stack, project structure and commands.
Plugin Claude Code
Interview-shaped AI coding harness for Claude Code / Cursor / Codex — grade-gated review, block-merge edit preservation, anti-rot crawlers, worktree isolation.
Plugin Claude Code
Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.
Instructions file
Repository-specific instructions for harness-maker, a plugin for Claude Code and Cursor that creates and manages AI-assisted development workflows.
Command
Refresh, reconfigure, or extend the project's harness at /.claude/. Asks the user what they want to do before invoking the CLI.
Hook
Runs when a session starts, running an inline shell check. From Ecro/harness-maker.
Agent Claude Code
Phase 1 cross-compat fixture. Outputs a single PASS line when invoked. Use proactively when the user mentions "phase 1 agent test".
Command Claude Code
Command "test-research" from Ecro/harness-maker, covering /hm:test-research, mission, step 1 — ask the user, step 2 — output a single line and step 3 — stop.
Settings file Claude Code
An empty agent settings file, from a project described as: Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.
Skill Claude CodeCodex
Phase 1 cross-compat fixture. Outputs a single PASS line when invoked. Tests Anthropic SKILL.md standard frontmatter compatibility across IDEs.
Cursor rule
Flutter team guidelines for Cursor.