Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/sigistry/marketplace/records)<a href="https://agentmods.dev/plugins/sigistry/marketplace/records"><img src="https://agentmods.dev/badge/plugins/sigistry/marketplace/records/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/sigistry/marketplace/records"><img src="https://agentmods.dev/badge/plugins/sigistry/marketplace/records.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
records scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "records",
"displayName": "Records",
"description": "Validate FHIR R4 resources, diagnose Implementation Guide projects, explain conformance issues, and generate reviewed CI quality gates.",
"version": "0.8.3",
"author": {
"name": "MedVertical"
},
"homepage": "https://github.com/medvertical/records-agent-tools",
"repository": "https://github.com/medvertical/records-agent-tools",
"license": "MIT",
"keywords": [
"fhir",
"fhir validation",
"fhir validator",
"hl7",
"hl7 fhir",
"fhir r4",
"healthcare interoperability",
"health data",
"data quality",
"fhir conformance",
"fhir profiles",
"structuredefinition",
"operationoutcome",
"implementation guide",
"ig authoring",
"ig publisher",
"sushi",
"terminology",
"github actions",
"ci/cd",
"records"
]
}
What it installs
The manifest is a name and a version. 3 skills, 5 commands, 1 agent travel with it, and installing the plugin installs all of them — 374 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill fhir-validation A 103 tokens
- Skill fhir-ci-quality A 65 tokens
- Skill fhir-project-doctor A 88 tokens
- Command doctor A 20 tokens
- Command init-ci A 11 tokens
- Command validate A 19 tokens
- Command derive-quality-rules A 14 tokens
- Command explain-outcome A 15 tokens
- Agent fhir-validation-reviewer A 39 tokens
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 36 lines scan A 22822a560fe6
records is a plugin published in the GitHub repository sigistry/marketplace (3 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other plugins, from other repositories
handbook-glab
GitLab CLI (glab) expertise for managing merge requests, issues, CI/CD pipelines, and repositories from the command line.
infrastructure
Infrastructure and DevOps specialists for AWS, GCP, Kubernetes, Docker, Terraform, GitHub Actions, GitLab CI, and security auditing.
engineering-practices
Git commits, conventional releases, refactoring, test-driven development, and engineering ways of working skills.
minottobot
Use whenever the user asks about QA, testing strategy, CI/CD health, team processes, developer experience, code review practices, test coverage, flaky tests, monitoring, or any audit of an engineering team's quality practices.
github-audit
Audit GitHub repo health (security, CI/CD, branch protection, dependencies, community), auto-fix safe issues behind saved policies, run quality gates, and ship behind a confirmation gate — with cross-run history.
overheid-plugins marketplace
Plugin marketplace listing 10 plugins: standaarden, zad-actions, developer-overheid, nerds, internet.