health-harness
v0.5.2Mindbowser Health Harness — an agent-agnostic discipline for building healthcare products with AI: the Build Loop + healthcare-compliance guardrails. Packaged as Claude Code skills.
By Mindbowser0 GitHub starsUpdated last week
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 22 skill or MCP entries
- Source updated
- Sep 15, 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 health-harness for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install health-harness@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/Mindbowser/health-harnessClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .claude-plugin/plugin.json├── skills/align/SKILL.md├── skills/audit-logging/SKILL.md├── skills/compliance-profile/SKILL.md├── skills/harness-config/SKILL.md├── skills/harness-feedback/SKILL.md├── skills/harness-help/SKILL.md├── skills/harness-questions/SKILL.md├── skills/harness-stats/SKILL.md├── skills/harness-update/SKILL.md├── skills/import-issues/SKILL.md├── skills/onboard-existing-codebase/SKILL.md├── skills/phi-redaction-check/SKILL.md├── skills/role/SKILL.md├── skills/safe-logging/SKILL.md├── skills/scaffold-from-boilerplate/SKILL.md├── skills/ship/SKILL.md├── skills/sprint/SKILL.md├── skills/start/SKILL.md├── skills/tdd/SKILL.md├── skills/to-issues/SKILL.md├── skills/to-prd/SKILL.md└── skills/writing-great-skills/SKILL.md
Included Skills22
Right-sized interview to reach a shared design concept before code — deep for fuzzy features, near-instant for clear ones.
Record who accessed or changed PHI/ePHI — the HIPAA audit trail. Distinct from safe-logging; both are needed.
Declare or read a repo's compliance profile (hipaa/pci/gdpr/none) so the right governance auto-applies.
Review and change the harness settings interactively — see every default, flip what's configurable, and see what org policy enforces. Also the first-run onboarding.
Send feedback about the harness itself — a bug, a friction point, an idea, "this was confusing" — enriched with version/user/context, PHI-scanned, and sent only after you confirm the exact payload.
Show what the Mindbowser Health Harness is and how to use it — the in-plugin guide, no repo access needed.
See and answer the open "I don't know yet" questions on the current ticket — the ones the build logged and left for you to ratify. Lists them and resolves each interactively; reconciles anything your answer changes.
Show YOUR own harness usage — a private /usage-style dashboard of activity, the coaching dimensions, trends, and a motivational summary. Read-only, metadata-only, no data leaves the machine.
Update the Mindbowser Health Harness plugin to the latest version in one step (no marketplace UI).
Pull this sprint's stories/bugs from the tracker (Jira/Linear) as context for alignment — reshape, don't re-elicit.
Make an existing/customer (brownfield) repo agent-ready — comprehend it, write a repo CLAUDE.md, and establish a feedback loop before any build.
Scan anything customer-facing for PHI/PII, secrets, and disallowed content before it leaves the repo; block on a hit.
Set or show your harness role (PM/BA or Engineer). Persists across sessions; sets align's default mode.
Log errors and traces without leaking PHI/PII/secrets — scrub at the logger boundary, log references not identities.
Start a new (greenfield) project from MB boilerplate, wired with the gate and a compliance profile.
Publish a finished slice — push the branch, open the PR, transition the Jira ticket, log the worklog — each step confirmed. The single, consistent end-of-work flow that /tdd hands off to.
Set or show the active sprint — the container the Build Loop files its align/PRD/issue artifacts under.
Start here — detect the project archetype (new / existing / Studio handover) and route to the right front door.
Test-driven development using red-green-refactor cycles — the way AFK build work is done.
Break a PRD into independently-grabbable issues using vertical slices, with blocking order.
Turn an alignment session into a disposable PRD — the destination document for the work.
How to author a skill for the Mindbowser Health Harness — structure, frontmatter, completion criteria, anti-patterns.
Plugin manifests1
{
"name": "health-harness",
"version": "0.5.2",
"description": "Mindbowser Health Harness — an agent-agnostic discipline for building healthcare products with AI: the Build Loop + healthcare-compliance guardrails. Packaged as Claude Code skills.",
"author": {
"name": "Mindbowser"
},
"homepage": "https://github.com/Mindbowser/health-harness"
}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.
[health-harness on Agent Plugins Marketplace](https://pluginsmp.com/plugins/health-harness)