darkroom
v0.19.0Evidence-based autonomous delivery: the darkroom interview, converge, status, and chronicle skills — version-locked to the darkroom-ai engine
By Emmanuel I. ObiLicense: Apache-2.00 GitHub starsUpdated 2 hours ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 4 skill or MCP entries
- Source updated
- Sep 29, 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 darkroom for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install darkroom@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/withtwoemms/darkroomClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is src/darkroom/.
Plugin files
├── .claude-plugin/plugin.json├── skills/darkroom-chronicle/SKILL.md├── skills/darkroom-converge/SKILL.md├── skills/darkroom-interview/SKILL.md└── skills/darkroom-status/SKILL.md
Included Skills4
Narrate a darkroom project's delivery from its dossier - summarize development progression, collate what the judge has witnessed, and surface sticking points and novelties to the operator. Use when a user asks how delivery is going, what happened across runs, why a scenario is stuck, or what the loop has been doing.
Run a scenario through the darkroom convergence loop as the operator - author the drive and rubric, pre-flight, commit both repos, launch auto, triage blockers, regress, and deploy. Use when a user wants to build or ship a feature via darkroom auto, converge a scenario, or after the intent interview has produced a rubric that now needs a drive and a run.
Conduct the darkroom intent interview - distill a product description into scenarios, rubrics, and an evidence contract for evidence-based delivery. Use when a user wants to set up a project for darkroom, author scenarios or rubrics, define "done" for a feature, or prepare a project for the convergence loop.
Report where a darkroom project stands right now - convergence per scenario, blockers, what is shipped versus merely gated, the ticket queue, and spend - in one fixed shape, from the engine's own status command. Use when a user asks for a status, a convergence update, "where are we", what's running, what's blocked, or what's next.
Plugin manifests1
{
"name": "darkroom",
"version": "0.19.0",
"description": "Evidence-based autonomous delivery: the darkroom interview, converge, status, and chronicle skills — version-locked to the darkroom-ai engine",
"author": {
"name": "Emmanuel I. Obi"
},
"homepage": "https://github.com/withtwoemms/darkroom",
"license": "Apache-2.0"
}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.
[darkroom on Agent Plugins Marketplace](https://pluginsmp.com/plugins/darkroom)