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 agentmods add skills/cqframework/clinical-reasoning/linked-builds-prnpx skills add cqframework/clinical-reasoning --skill linked-builds-prgit clone --depth 1 https://github.com/cqframework/clinical-reasoningWrote 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/cqframework/clinical-reasoning/linked-builds-pr)<a href="https://agentmods.dev/skills/cqframework/clinical-reasoning/linked-builds-pr"><img src="https://agentmods.dev/badge/skills/cqframework/clinical-reasoning/linked-builds-pr.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00044 | $0.02097 |
| Opus 5 | $0.00022 | $0.01048 |
| Sonnet 5 | $0.00009 | $0.00419 |
| Haiku 4.5 | $0.00004 | $0.00210 |
Grade A, and why
linked-builds-pr 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 4d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating PRs with Linked Builds
Overview
This project supports linked builds — composite Gradle builds that substitute Maven Central
artifacts with local source checkouts of sibling repositories. When creating PRs that span
multiple repositories, each PR must declare its cross-repo dependencies using Depends-On:
directives so CI can build them together.
Key Files
local.properties(gitignored): Developer's active linked buildslocal.properties.example: Template showing available linked buildsbuild-logic/src/main/kotlin/cqf/LinkedBuild.kt: Registry of all known linked builds (LinkedBuildRegistry) — contains repo slugs, property keys, build roots, and substitution mappingsbuild-logic/src/main/kotlin/cqf.linked-builds.settings.gradle.kts: Settings plugin that readslocal.propertiesand callsincludeBuild()with dependency substitutionsbuild-logic/src/main/kotlin/cqf.ci-conventions.gradle.kts: CI plugin with theresolveLinkedBuildstask that parsesDepends-On:from PR descriptions
Workflow
When a developer asks you to create PRs for their linked build changes, follow this procedure.
The goal is to create PRs from the most upstream repo down to this repo, with each
downstream PR declaring Depends-On: for its upstream dependencies. Once all PRs are created,
go back and update the upstream PRs to indicate they block downstream work by appending a Blocks: section.
Step 1: Discover Active Linked Builds
Read local.properties in the project root. Each property key maps to a LinkedBuild entry
in the registry. For example:
cql.engine.path=../clinical_quality_language/Src/java
Look up each active property key in LinkedBuildRegistry (in LinkedBuild.kt) to get the
repo slug, build root, etc.
If no linked builds are active (i.e., local.properties doesn't exist, is empty,
comments out all properties, or only has unrelated properties), then no cross-repo PRs are needed,
exit this workflow, and create a single PR for this repo as usual.
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.
- 4d ago First seen · 226 lines · 44 tokens per session scan A de4d143fefcb
linked-builds-pr is a skill published in the GitHub repository cqframework/clinical-reasoning (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 2,097 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
hl7gen
Use when generating, validating, or converting HL7 v2 healthcare messages, or converting HL7 v2 to FHIR. Covers synthetic test-message generation for any of 185 HL7 v2 message types across versions 2.1–2.8.2, message validation, FHIR R5/R4B conversion, and structure exploration (required/optional/repeating fields).…
healthcare-expert
Expert-level healthcare systems, medical informatics, HIPAA compliance, and health data standards.
ehr-data-parsing
Parse and extract clinical data from HL7v2 messages and FHIR R4 resources using Python. Use when the user mentions HL7v2, HL7, FHIR, PID segment, OBX segment, MSH segment, Patient resource, Observation resource, Condition resource, MedicationRequest, EHR data extraction, clinical message parsing, FHIR bundle, HL7 to…
comment-compactor
Delete the comments a diff adds unless they earn their place, and condense the few that do. Use as the final step before pushing, submitting, or finalizing a PR — after tests and lint pass, before git push / gh pr create. Also use when asked to "clean up the comments", "check the comments", or when a review flags a…
lab-report-walkthrough
Walk a person through their lab report — read the original document, organize results by panel, flag out-of-range values against the printed reference ranges, compare with their history, and explain in plain language. Use when the user uploads a lab report (PDF/image) or asks what their blood test results mean.
overview
SpecKit overview-canvas skill for OpenELIS. Generates an interactive HTML dashboard from a feature's spec.md / plan.md / research.md / tasks.md that surfaces user stories, milestones, data model, decisions, API, and AC coverage in 2-level progressive disclosure (tabs → expandable cards). Light + dark mode + inline…