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 openEHR/ai-plugins --skill publishgit clone --depth 1 https://github.com/openEHR/ai-pluginsWrote 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/openehr/ai-plugins/publish)<a href="https://agentmods.dev/skills/openehr/ai-plugins/publish"><img src="https://agentmods.dev/badge/skills/openehr/ai-plugins/publish/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/openehr/ai-plugins/publish"><img src="https://agentmods.dev/badge/skills/openehr/ai-plugins/publish.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00021 | $0.00625 |
| Opus 5.5 | $0.00008 | $0.00250 |
| Sonnet 5.5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
publish 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 9d 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
Build a local HTML preview of the component named in $ARGUMENTS (for example RM, BASE or AM)
with the published ghcr.io/openehr/asciidoctor image. This is the preview step of the
openehr-specs:authoring skill: it builds a whole component as the development release and never
tags, commits, or deploys (that is governance). If $ARGUMENTS is empty, ask which component and
stop: the image takes exactly one.
- Work from the parent directory that holds the sibling
specifications-AA_GLOBAL/(the image reads the boilerplate and references from it) andspecifications-<component>/checkouts. If either is missing, say which and stop. Ifwhich dockerfinds nothing, say Docker is required and stop. - Snapshot the outputs:
stat -c '%Y %n' specifications-<component>/docs/*.html(ignore "No such file"; usels -lwherestat -cis unavailable). - Build. The entrypoint is
spec_publish.sh -f -r -v -t -q -l, so the first argument is the release:docker run --rm -u $(id -u):$(id -g) -v "$(pwd):/documents/" ghcr.io/openehr/asciidoctor development $ARGUMENTS - Verify, because the build prints
generated <file>and exits 0 even when includes are missing orasciidoctorfailed. Globspecifications-<component>/docs/*/master.adoc: each needs a rebuiltdocs/<dir>.htmlbeside it, plusdocs/index.htmlwhendocs/index.adocexists. Repeat thestatcommand; a file that is missing or unchanged isNOT BUILT. AnyERRORorinclude file not foundlog line (for example{pkg}…class tables) also fails the build. AnINFOline, such as a possible invalid bibliography reference, does not. - Report where the HTML landed and every error or warning verbatim. On failure, summarise the first
actionable error and point to
authoring(includes, attributes) or thexref-auditorsubagent (cross-references). The build rewrites the trackeddocs/*.htmlartefacts: tell the user, and do not stage them.
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.
- 9d ago First seen · 37 lines · 21 tokens per session scan A 0ce00b95d89e
publish is a skill published in the GitHub repository openEHR/ai-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 625 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
pptx-posters
Creates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
swmm-report
Generate a client-deliverable Word (.docx) report from an audited SWMM run directory. Reads manifest.json, experimentprovenance.json, modeldiagnostics.json, comparison.json, and any PNG figures — SWMM is never re-run. Supports custom YAML/JSON section templates.
thesis-consistency-audit
A consistency audit for quantitative master’s and doctoral theses in management, finance, or strategy. It checks whether numbers, tables, analyses, and claims agree, and can inspect hidden author information in office documents.