yimwoo

yimwoo/hotl-plugin

Plugin Claude Code

Human-on-the-Loop (HOTL) operating model for AI-native development.

yimwoo/hotl-plugin

Plugin Claude Code

Human-on-the-Loop operating model: skills, workflows, and adapters for AI-native development.

yimwoo/hotl-plugin

Agent

Use after completing a step or batch of implementation work. Reviews against the HOTL workflow and HOTL contracts. Flags BLOCK/WARN/NOTE issues with file:line references.

yimwoo/hotl-plugin

Command

Design a feature with HOTL contracts before writing any code.

yimwoo/hotl-plugin

Command

Check if a newer HOTL version is available.

yimwoo/hotl-plugin

Command

Execute plan linearly with explicit human checkpoints.

yimwoo/hotl-plugin

Command

Execute a HOTL workflow with loop execution and auto-approve.

yimwoo/hotl-plugin

Command

Review a PR across multiple dimensions (description, code, scan, tests).

yimwoo/hotl-plugin

Command

Resume an interrupted HOTL workflow run.

yimwoo/hotl-plugin

Command

Generate HOTL adapter files for your team's code assistants (Codex, Cline, Cursor, Copilot).

yimwoo/hotl-plugin

Command

Execute a reviewed HOTL workflow in this session with delegated subagent steps and controller-owned verification.

yimwoo/hotl-plugin

Command

Create a docs/plans/YYYY-MM-DD- -workflow.md implementation workflow with loops and gates.

yimwoo/hotl-plugin

Hook

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From yimwoo/hotl-plugin.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use before any feature work — explores intent, requirements, and design. Produces HOTL contracts (intent, verification, governance) before implementation.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use after completing implementation steps and before merging — reviews against plan and HOTL contracts.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use when you have 2+ independent tasks with no shared state — dispatches parallel subagents for each task.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Optional utility for reviewing existing docs, external specs, hand-authored notes, or non-HOTL documents. HOTL design docs and workflows get structural lint + AI review; other documents get AI-only review with a generic rubric.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use when executing an implementation plan linearly with explicit human checkpoints between batches of tasks.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use after execution is complete or intentionally stopped — decide whether to merge back, publish a PR branch, keep the execution checkout, or discard it, and record that disposition in HOTL state.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use when executing an accepted HOTL workflow through the best available host or fallback driver.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approves low-risk gates, pauses at high-risk gates.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use when review findings arrive — verify each claim against the codebase and HOTL contracts before making changes. Governs how agents respond to review feedback.

yimwoo/hotl-plugin

Skill Claude CodeCodex

Use at executor review checkpoints to dispatch the code-reviewer agent with structured context — git range, workflow contracts, and verification evidence.