Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By yimwoo
Enforces a Human-on-the-Loop (HOTL) development workflow where AI agents produce design contracts, execute implementation plans with human checkpoints, and gate code changes through structured review and verification before merge.
npx claudepluginhub yimwoo/hotl-plugin --plugin hotlDesign a feature with HOTL contracts before writing any code
Check if a newer HOTL version is available
Execute plan linearly with explicit human checkpoints
Execute a HOTL workflow with loop execution and auto-approve
Review a PR across multiple dimensions (description, code, scan, tests)
Use before any feature work — explores intent, requirements, and design. Produces HOTL contracts (intent, verification, governance) before implementation.
Use after completing implementation steps and before merging — reviews against plan and HOTL contracts.
Use when you have 2+ independent tasks with no shared state — dispatches parallel subagents for each task.
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.
Use when executing an implementation plan linearly with explicit human checkpoints between batches of tasks.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
HarnessFlow — From idea to shipped product: high-quality engineering workflows for AI agents. Spec-anchored SDD, gated TDD, evidence-based routing, independent reviews, and formal closeout.
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
Hypo-Workflow for Claude Code. The plugin namespace is intentionally `hw`; plugin-root commands map /hw:* to existing workflow Skills.
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
Agentic engineering done right — 57 structured workflows, 17 specialist agent personas, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Share bugs, ideas, or general feedback.
HOTL (Human-on-the-Loop) is an AI coding workflow plugin and skill pack for Codex, Claude Code, and Cline. It keeps implementation work grounded in a design, an executable workflow, review checkpoints, and verification evidence.
Use HOTL for feature work, refactors, and risky changes where "just start coding" is too loose. It stays out of the way for code questions, debugging, and obvious one-line fixes.
Adapter templates are also available for Cursor and GitHub Copilot.
Most AI coding sessions fail in predictable ways: code starts before requirements are clear, plans skip verification, risky changes execute without review, and the agent claims success without evidence.
HOTL prevents all four by enforcing structured workflows for implementation tasks while staying out of the way for code questions, quick fixes, and debugging.
If someone searches for a "HOTL plugin" or a "Human-on-the-Loop AI coding workflow", this repo is the main project: it contains the canonical HOTL skills, workflow templates, and installation docs for Codex, Claude Code, and Cline.
Pick the install path for the tool you use. Codex users should prefer plugin install; native skills are only for older Codex builds or local HOTL development.
/plugin marketplace add yimwoo/hotl-plugin
/plugin install hotl@hotl-plugin
Recommended plugin install for both Codex CLI and Codex app users:
git clone https://github.com/yimwoo/hotl-plugin /tmp/hotl-plugin
bash /tmp/hotl-plugin/install.sh --codex-plugin
Restart Codex, then install or enable HOTL from the plugin directory.
Codex CLI:
codex
/plugins
In the plugin browser, switch to Local Plugins, open HOTL, and select
Install plugin. If HOTL is installed but disabled, press Space to enable it.
Codex app: open Plugins, switch to Local Plugins, and install HOTL. The CLI and app share the same Codex plugin configuration when they use the same Codex profile.
Plugin install does not automatically remove an older native-skills install. If both are present, Codex may discover duplicate HOTL sources. See docs/README.codex.md for the recommended migration path.
Native skills fallback for older Codex builds or local HOTL development: clone to ~/.codex/hotl and symlink ~/.agents/skills/hotl to its skills/ directory. In that mode, ~/.codex/hotl is the stable channel and should track origin/main. Full guide: docs/README.codex.md.
curl -fsSL https://raw.githubusercontent.com/yimwoo/hotl-plugin/main/install-cline.sh | bash
Full guide: docs/README.cline.md
After install, start with a design request. HOTL will choose the right workflow stage and save durable artifacts in the project.
| Tool | Try this |
|---|---|
| Codex | @hotl brainstorm this feature before coding: <your feature> |
| Claude Code | /hotl:brainstorm <your feature> |
| Cline | brainstorm this feature before coding: <your feature> |
Typical outputs:
docs/designs/YYYY-MM-DD-<slug>-design.mddocs/plans/YYYY-MM-DD-<slug>-workflow.md.hotl/state/ and .hotl/reports/Implementation tasks follow eight phases: