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/Cadasto/openehr-assistant-pluginWrote 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/commands/cadasto/openehr-assistant-plugin/openehr-explain)<a href="https://agentmods.dev/commands/cadasto/openehr-assistant-plugin/openehr-explain"><img src="https://agentmods.dev/badge/commands/cadasto/openehr-assistant-plugin/openehr-explain/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/commands/cadasto/openehr-assistant-plugin/openehr-explain"><img src="https://agentmods.dev/badge/commands/cadasto/openehr-assistant-plugin/openehr-explain.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 | $0.00095 | $0.02771 |
| Opus 5 | $0.00048 | $0.01385 |
| Sonnet 5 | $0.00019 | $0.00554 |
| Haiku 4.5 | $0.00010 | $0.00277 |
Grade A, and why
openehr-explain 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/openehr-explain
Explain or look up whatever the user names: $ARGUMENTS. Auto-detect the kind of input, route it to the matching lookup, and produce the explanation in that kind's output shape. Read-only — never suggest modifications.
Step 1 — Classify the input
Pick exactly one kind using these heuristics (first match wins):
- Archetype — an id like
openEHR-EHR-OBSERVATION.*(anyopenEHR-<RM>-<class>.<concept>.v#), or a workspace path ending in.adl. (Other.adlreferences such as ADL2 are also archetypes.) - Template — an id ending in a template/OPT identifier, or a path ending in
.oet/.t.json/.opt/.optx/.optj(or a web-template JSON file). - RM/AM/BASE type — a single ALL-CAPS token in the openEHR type style:
DV_QUANTITY,COMPOSITION,OBSERVATION,ELEMENT,C_ATTRIBUTE. Underscores and a leadingDV_/C_are strong signals; no version, no path. - RM structural concept — how the model is structured rather than one class: e.g.
"composition categories", "ISM states", "versioning", "PARTY hierarchy", "identities vs
identifiers", "privacy / EHR–demographic separation"; often prefixed with a domain
(
ehr/demographic). Distinguish from a bare class token (that's an RM/AM type). - ADL idiom / pattern — phrasing about how to constrain: "coded text constraint", "ordinal scale", "quantity range", "slot", "how do I constrain …", "what's the ADL for …".
- AQL query / keyword — an AQL statement (contains
SELECT/FROM/CONTAINS/WHERE), or a question about AQL syntax — a clause/operator/function ("what doesCONTAINSdo", "AQL for latest-per-EHR"). Explanation only; to write / optimize / review a query, that is theaql-authoringskill, not this command. - Terminology — an openEHR terminology code/term, a
local::/at####code, a known terminology id (e.g.openehr, SNOMED-CT, LOINC) code, or the URIopenehr://terminology.
If the input is a workspace file path, you may Read it (and Glob/Grep to locate it)
to confirm the kind before routing. If genuinely ambiguous (e.g. an ALL-CAPS token that
could be a type or a terminology rubric), ask one brief clarifying question, then route.
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 · 121 lines · 95 tokens per session scan A 63b75c6b2cbf
openehr-explain is a command published in the GitHub repository Cadasto/openehr-assistant-plugin (4 stars, last pushed 14d ago), licensed MIT. It adds 95 tokens to every session and 2,771 once invoked, about $0.0005 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 2026-08-31.
Other commands, from other repositories
daily-okr
Run a daily knowledge compound loop (7 KR). Invoke with /daily-okr or "start my daily review".
research
Start or resume an academic research project — idea through literature, methodology, writing, feedback, and publishing.
specialization
Train agents to become experts in specific domains for better performance.
talk
Turn a paper (or several) into an academic talk — outline, slides, speaker notes, backups, rehearsal plan.
co-change
List files that historically co-change with a target (git log heuristic; COCHANGE-style).
create-scene
Create a single animated scene for mathematical visualization.