workflow-lab
v1.0.0Local/interactive workflow skills: setup, iterate, transcript-parser, workflow-tuning. Never required by the cloud pipeline.
By William Hamilton0 GitHub starsUpdated 5 days ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 4 skill or MCP entries
- Source updated
- Sep 18, 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 workflow-lab for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install workflow-lab@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/codyhamilton/workflow-pluginClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/workflow-lab/.
Plugin files
├── .claude-plugin/plugin.json├── skills/iterate/SKILL.md├── skills/setup/SKILL.md├── skills/transcript-parser/SKILL.md└── skills/workflow-tuning/SKILL.md
Included Skills4
Drive long-horizon work whose success criteria are not knowable up front, by building divergent candidate solutions, synthesising, consolidating and hardening, then extrapolating next steps.
Bootstrap stable docs (docs/OVERVIEW.md and docs/ARCHITECTURE.md) for a repo that does not have them yet. Use when starting plan on a new repo or when plan reports that stable docs are absent or thin.
Parse an AI tool session transcript to extract cost metrics (agents spawned, tool turns per agent, tool type breakdown, context estimate, wall time) in eval cost-comparison format. Use after a plan-execute run to populate a cost-comparison.md, or during workflow-tuning to compare execution approaches.
Captures observed lessons about plan/execute/review workflows, documentation economy, execution cost, phasing, and review posture. Use when refining plan, execute, or review skills; designing workflow evals; or comparing real plan artifacts to decide what workflow improvements are worth making.
Plugin manifests1
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "workflow-lab",
"description": "Local/interactive workflow skills: setup, iterate, transcript-parser, workflow-tuning. Never required by the cloud pipeline.",
"version": "1.0.0",
"author": {
"name": "William Hamilton",
"email": "[email protected]"
}
}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.
[workflow-lab on Agent Plugins Marketplace](https://pluginsmp.com/plugins/workflow-lab)