51 specialist AI agents for US healthcare administration.
Installable prompts and skills for Claude Code, Codex, OpenCode, Cursor, Copilot, and other agentic coding tools.

Healthcare Agents is a model-agnostic prompt library for healthcare administration work: revenue cycle, quality and compliance, clinical operations, payer relations, health IT, population health, pharmacy programs, operations, strategy, and emergency preparedness.

Each agent is a long-form Markdown specialist with YAML frontmatter, role-specific source awareness, compliance boundaries, operational workflows, concrete deliverable templates, best-input guidance, output modes, and cross-agent handoff rules. The pack installs into tools that support subagents, custom instructions, repository rules, or SKILL.md folders.

These agents are for healthcare administration support. They are not clinicians, attorneys, auditors, coders of record, billing authorities, or a safe PHI-processing environment.

Fast path:

curl -fsSL https://raw.githubusercontent.com/ajhcs/healthcare-agents/main/install.sh | bash

GitHub-backed npx:

npx --yes github:ajhcs/healthcare-agents install

The package metadata is ready for npm, but the package is not currently published to the npm registry from this environment. Use the GitHub-backed npx command above.

Target a specific tool:

Preview before writing files:

npx --yes github:ajhcs/healthcare-agents install --all --dry-run

Update existing installs:

npx --yes github:ajhcs/healthcare-agents install --all --force

Uninstall:

npx --yes github:ajhcs/healthcare-agents uninstall --all

Start with the task, not the agent name. Use the agent selection guide when you know the operational problem, the starter prompts when you want copy-ready examples, and the handoff map when the request spans departments.

Every agent now supports four output modes:

Common starting points:

Claude Code:

Use the revenue-cycle-specialist agent in quick triage mode to diagnose why our clean claim rate dropped, then list coding, contract, and prior authorization handoffs.

Codex:

Read the quality-compliance-officer healthcare agent and use audit/checklist mode to draft a HIPAA Security Rule evidence checklist for a small clinic.

OpenCode:

Use the revenue-contract-analyst skill to model payer contract underpayment risk from a sample allowed-amount table.

Rules-based tools:

Using the healthit-interoperability-engineer instructions, review this HL7v2 interface mapping for common ADT and ORU risks.

Manual project install:

git clone https://github.com/ajhcs/healthcare-agents.git
mkdir -p .claude/agents
cp healthcare-agents/agents/*.md .claude/agents/

flowchart LR
  A["agents/*.md<br/>source prompts"] --> B["Claude Code<br/>~/.claude/agents"]
  A --> C["Codex<br/>~/.codex/agents + AGENTS.md"]
  A --> D["Rules folders<br/>Cursor · Windsurf · Copilot"]
  A --> E["Generated SKILL.md"]
  E --> F["Claude Skills<br/>Desktop · Cowork"]
  E --> G["OpenCode Skills"]
  E --> H["Open Agent Skills<br/>.agents/skills"]

All 51 agents have been improved through the repository's lightweight self-improvement loop.

The eval kit is intentionally simple and auditable:

Same-question before/after comparisons must preserve full Q001-Q025 artifacts before answers are generated. This keeps score deltas tied to the exact same exam rather than paraphrased weak areas.

Install the eval loop into another project that already has agents/*.md:

git clone https://github.com/ajhcs/healthcare-agents.git
bash healthcare-agents/scripts/install-self-improvement-kit.sh /path/to/project

Run in Claude Code:

/eval revenue-medical-coding-specialist

Run in Codex:

Run the healthcare self-improvement loop for revenue-medical-coding-specialist.

During a normal eval run, only the requested agents/<slug>.md file should change, eval/results.tsv should only receive appended rows, and local artifacts should stay under ignored eval/run-logs/ paths.

.
├── agents/                         # 51 source agent prompts
├── .claude/commands/eval.md         # canonical self-improvement workflow
├── eval/
│   ├── rubric.md                    # frozen scoring rubric
│   ├── results.tsv                  # append-only eval log
│   ├── role-baselines/              # expected capability baselines
│   └── run-logs/                    # local ignored exact-question artifacts
├── docs/eval/                       # scorer and model-routing guidance
├── docs/usage/                      # agent chooser, starter prompts, handoff map
├── bin/cli.js                       # GitHub-backed npx entrypoint
├── install.sh                       # multi-tool installer
└── scripts/                         # lint and self-improvement kit helpers

Validate agent prompt structure:

bash scripts/lint-agents.sh

Preview installer behavior:

bash install.sh --all --dry-run

Check CLI help:

npx --yes github:ajhcs/healthcare-agents --help

• The agents provide healthcare administration support, not final clinical, legal, coding, billing, audit, or compliance determinations.
• Regulations, code sets, payer policies, accreditation standards, and program manuals change. Verify against current primary sources before operational use.
• The prompts do not make an AI tool HIPAA-compliant and do not create a safe PHI-processing environment. Use approved privacy, security, de-identification, and vendor-review workflows.
• Tool support differs by runtime. The installer uses best-known current file layouts and keeps plain Markdown as the fallback.
• The eval scores measure performance against this repository's rubric and role baselines; they are not external certification.

Both. The source files in agents/*.md install as Claude Code subagents. The installer can also generate one SKILL.md folder per agent for Claude Skills, Claude Desktop/Cowork where skills are available, OpenCode, and the open .agents/skills convention.

Yes. The installer copies prompts to ~/.codex/agents and writes a managed ~/.codex/AGENTS.md block telling Codex how to select and read specialists. For repo-local Codex App work, keep the prompts in the repository and reference them from AGENTS.md.

Claude Code and OpenCode expect lowercase hyphen identifiers. v1.1.1 and newer keep human labels in display_name while making name match the filename slug.

Use them for structured analysis, checklists, source-aware workflows, and draft deliverables. Do not treat them as final legal, clinical, coding, billing, audit, or compliance determinations.

Only inside an environment your organization has approved for PHI, with the right vendor agreements, access controls, retention settings, and de-identification practices. The prompts themselves do not solve that governance problem.

Yes. Follow the conventions in CONTRIBUTING.md, run bash scripts/lint-agents.sh, and keep the agent narrow, source-aware, and operationally concrete.

Apache 2.0. See LICENSE.