harness
Enforcement layer for AI-assisted development: hooks, gates, and evals that make the workflow mandatory, not advisory
By juandarn0 GitHub starsUpdated yesterday
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 3 skill or MCP entries
- Source updated
- Sep 23, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install harness for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install harness-11@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/juandarn/harnessClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugin/claude-code/.
Plugin files
├── .claude-plugin/plugin.json├── skills/harness-pipeline/SKILL.md├── skills/live-test/SKILL.md└── skills/review-gate/SKILL.md
Included Skills3
Trigger: starting development work in a repo with harness.gates.json, or the user mentions the harness pipeline, harness workflow, or asks how harness enforces the process. Loads the core enforced protocol: SDD, strict TDD, subagent-only edits, review gate, live-test, PR.
Trigger: "live test", "prueba en vivo", "test in docker", or finishing a feature in a repo with harness.gates.json. Runs the service in Docker against the real deploy shape before PR and writes .harness/live-test.md evidence.
Trigger: "review gate", finishing implementation, or right before opening a PR. Launches fresh-context transversal review via subagents and writes .harness/review-report.md evidence.
Plugin manifests1
{
"name": "harness",
"description": "Enforcement layer for AI-assisted development: hooks, gates, and evals that make the workflow mandatory, not advisory",
"author": {
"name": "juandarn"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[harness on Agent Plugins Marketplace](https://pluginsmp.com/plugins/harness-11)