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.
npx skills add softspark/ai-toolkit --skill medplum-rulesgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/skills/softspark/ai-toolkit/medplum-rules)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/medplum-rules"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/medplum-rules/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/skills/softspark/ai-toolkit/medplum-rules"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/medplum-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 96 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.03916 |
| Opus 5 | $0.00026 | $0.01958 |
| Sonnet 5 | $0.00011 | $0.00783 |
| Haiku 4.5 | $0.00005 | $0.00392 |
Grade A, and why
medplum-rules 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Medplum (FHIR healthcare) Rules
These rules come from app/rules/medplum/ in ai-toolkit. They cover
the project's standards for coding style, frameworks, patterns,
security, and testing in Medplum (FHIR healthcare). Apply them when writing or
reviewing Medplum (FHIR healthcare) code.
Medplum / FHIR Coding Style
Resource Structure
- Every FHIR object must include
resourceTypeas first field. - Use PascalCase for resource types (
Patient,ServiceRequest), camelCase for fields (birthDate,valueQuantity). - Never hardcode resource IDs. Let the server assign them on create.
- Include
meta.profilewhen creating resources that must conform to a StructureDefinition.
References
- Use
createReference(resource)from@medplum/coreto build Reference objects. - Always include
displayon references for human readability. - Use
getReferenceString(resource)for comparisons and logging — returnsResourceType/id. - Use
parseReference(ref)to extract resourceType and id from a reference string. - Never concatenate strings to build references manually.
CodeableConcepts & Coding
- Always include
system,code, anddisplayin every Coding element. - Use standard terminology URIs:
http://loinc.org,http://snomed.info/sct,http://hl7.org/fhir/sid/icd-10-cm. - Use
getCodeBySystem(cc, system)to find codes;setCodeBySystem(cc, system, code)to set them. - Prefer
CodeableConceptover plainCodingwhen the FHIR spec allows both — it supports multiple codings and free text.
Identifiers
- Use
identifierarrays withsystem+valuefor external IDs (MRN, NPI, SSN). - Use
getIdentifier(resource, system)andsetIdentifier(resource, system, value)helpers. - Identifier systems must be absolute URIs (e.g.,
http://hl7.org/fhir/sid/us-npi). - Use
createResourceIfNoneExist(resource, 'identifier=system|value')for idempotent creates.
Extensions
- Use the
extensionarray withurland typedvalue[x]fields. - Prefer official HL7/US Core extensions over custom ones where they exist.
- Use
getExtension(resource, url)andgetExtensionValue(resource, url)helpers.
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.
- 6d ago First seen · 272 lines · 53 tokens per session scan A e60bf2732b5a
medplum-rules is a skill published in the GitHub repository softspark/ai-toolkit (170 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 3,916 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
api-design
REST API contract designer and reviewer. ALWAYS use when designing new endpoints, reviewing existing API contracts, planning API versioning, or standardizing error models. Covers resource modeling (URL/naming), HTTP method semantics, status code selection, error model consistency, pagination/filtering/sorting…
kafka-event-driven-design
Kafka event-driven architecture designer and reviewer, at the application/client layer. ALWAYS use when designing, reviewing, or troubleshooting how a service produces or consumes Kafka events — topic and partition-key design, producer and consumer client configuration, consumer group topology, event schema definition…
api-caller-subagent
Sous-agent spécialisé dans les appels API REST/GraphQL avec retry, auth et transformation de données. Se déclenche avec "sous-agent API", "API caller agent", "agent qui appelle une API", "REST agent", "HTTP agent", "API integration subagent", "external API agent". Also triggers on "subagent that calls an API", "API…
message-protocol
Design de protocoles de communication entre agents et sous-agents — formats de messages, routing, delivery guarantees, ACK/NACK, versioning et middleware. Se déclenche avec "protocole agent", "message protocol", "communication agent", "agent messaging", "inter-agent communication", "message format agent", "agent API…
tool-calling-architect
Design et implémentation de systèmes de tool calling pour agents IA. Function calling, API wrapping, schema design, MCP server, parallel calls, sécurité et monitoring. Se déclenche avec "tool calling", "function calling", "tools agent", "API tools", "agent tools", "créer un outil", "custom tool", "tool schema", "MCP…
cost-optimizer
Optimisation des coûts des agents IA — tokens, API calls, modèles, caching, routing, budget controls. Se déclenche avec "coût agent", "agent cher", "réduire les coûts IA", "token optimization", "optimiser les tokens", "budget agent", "agent cost", "économiser sur l'API". Also triggers on "reduce agent cost", "token…