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/archetype-impact)<a href="https://agentmods.dev/commands/cadasto/openehr-assistant-plugin/archetype-impact"><img src="https://agentmods.dev/badge/commands/cadasto/openehr-assistant-plugin/archetype-impact.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 5.1 | $0.00051 | $0.01190 |
| Opus 5 | $0.00026 | $0.00595 |
| Sonnet 5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
archetype-impact 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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/archetype-impact
Compute the impact of editing a given archetype by finding every workspace artefact that references it — templates that include it, AQL queries that path into it, and any other place the archetype id or its at-codes appear.
Instructions
- Extract
<archetype-id>from $ARGUMENTS. Validate it matches the patternopenEHR-<DOMAIN>-<RM_TYPE>.<concept>.v<N>. - Glob the workspace for candidate files:
(Glob: **/*.oet Glob: **/*.opt Glob: **/*.t.json Glob: **/*.adl Glob: **/*.aql Glob: **/*.sql Glob: **/*.md.t.jsoncatches Archetype Designer source templates — AOM2 differential JSON withtemplateOverlays, not web templates;.adlcatches parent archetypes that slot this one in viaallow_archetype/include;.mdcatches AQL examples and documentation. A web template is derived runtime JSON with no extension convention — if the workspace holds one, the reference is generated, not authored, so treat it as downstream of its OPT.) - For each file, grep for the archetype id:
Grep: pattern="<archetype-id>", path=<file> - For templates (
.oet/.opt/.t.json) that mention the archetype, also inspect whether it's:- a top-level included archetype (in
<Items>/ the template's content tree), - nested as a slot filler (in
<Rule ... archetypeId>or a JSON slot reference), - in a
.t.json, carried as atemplateOverlaysentry (the differential overlay for that archetype) or named byparentArchetypeId, - referenced only as documentation text.
Distinguish source templates (
.oet,.t.json— where an edit propagates on the next compile) from compiled ones (.opt— where the reference is inlined and stale until regenerated); the recommendation differs.
- a top-level included archetype (in
- For other archetypes (
.adl), check whether they reference this archetype as a slot constraint — grep for the id insideallow_archetype/includeblocks; if found, the other archetype is a parent whose slot this one fills. - For AQL/SQL/md files, extract the full line(s) containing the reference so the user can see the containment and predicate context.
- Optionally call
ckm_archetype_get("<archetype-id>")once to resolve the concept name and report it alongside the impact table for clarity.
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.
- 8d ago First seen · 96 lines · 51 tokens per session scan A 259258cac976
archetype-impact is a command published in the GitHub repository Cadasto/openehr-assistant-plugin (4 stars, last pushed 13d ago), licensed MIT. It adds 51 tokens to every session and 1,190 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 2026-08-31.
Other commands, from other repositories
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
exasol
Route any Exasol task through the shared top-level Exasol skill.
bucketfs
Short entry point for repeated Exasol BucketFS file-management commands.
co-change
List files that historically co-change with a target (git log heuristic; COCHANGE-style).
sparc-supabase-admin
🔐 Supabase Admin - You are the Supabase database, authentication, and storage specialist. You design and implement d...
cache
Hostile audit of caching correctness: assume every cache serves stale data after a write, shares a key across entities that must not share one, grows without bound, and stampedes on expiry — then prove where. A cache is a correctness liability until its key, its invalidation, its bound, and its expiry behavior are all…