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 commands/openehr/ai-plugins/regen-classesgit clone --depth 1 https://github.com/openEHR/ai-pluginsWhat 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 | $0.00022 | $0.00533 |
| Opus 5 | $0.00011 | $0.00267 |
| Sonnet 5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
regen-classes 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 2d 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
Regenerate the class documentation (class-definition tables + UML class/package diagrams) for an
openEHR component from its BMM schema using the bmm-publisher tool. The tool, commands, output
layouts, and how the output wires into docs/UML/ are documented in the
openehr-specs:class-generation skill and its references/bmm-publisher.md — follow them; this
command is the action wrapper.
Arguments: $ARGUMENTS — the schema id (without .bmm.json, e.g. openehr_rm_1.2.0) and any
-d <dependency-schema> flags for cross-reference resolution (e.g. RM depends on BASE:
openehr_rm_1.2.0 -d openehr_base_1.3.0).
Do the following:
- Confirm Docker is available (
docker --version). If not, point the user to the localbmm-publisherdev-container path inreferences/bmm-publisher.mdand stop. - Determine the output target. Default to a working directory the user can inspect (e.g.
./out); ask before writing directly into aspecifications-XXrepo'sdocs/UML/. - Run the generator, mapping output ownership to the host user:
Usedocker run --rm --user $(id -u):$(id -g) \ -v ./out:/app/output \ ghcr.io/openehr/bmm-publisher asciidoc -v $ARGUMENTSlegacy-adoc -o <dir>instead when the component consumes the legacydocs/UML/classeslayout (per the class-generation skill). - Report what was generated (list the produced
classes/,effective/, diagram SVGs) and remind the user that generated files are never hand-edited — change the BMM and regenerate. - Do not commit. If the user wants the output wired into a spec repo, follow the placement steps in the class-generation skill.
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.
- 2d ago First seen · 37 lines · 22 tokens per session scan A 1e6fdac94181
regen-classes is a command published in the GitHub repository openEHR/ai-plugins (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 533 once invoked, about $0.0001 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
planflow
Draft a plan and get it approved as an editable flowchart in the browser before executing.
sql-developer
Comprehensive SQL Server development assistance for T-SQL queries, stored procedures, performance tuning, and code review with Microsoft documentation verification.
powershell-developer
Comprehensive PowerShell development assistance for scripts, modules, GUIs, and Windows automation with Microsoft best practices verification.
rust-developer
Comprehensive Rust development assistance for systems programming, async applications, web services, and CLI tools with Rust documentation verification.
swift-developer
Comprehensive Swift development assistance for iOS/macOS apps, Swift packages, SwiftUI, Swift 6 concurrency, and code review with Apple documentation verification.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.