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/openehr/ai-plugins/content-patternsnpx skills add openEHR/ai-plugins --skill content-patternsgit 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 | $0.00111 | $0.00840 |
| Opus 5 | $0.00056 | $0.00420 |
| Sonnet 5 | $0.00022 | $0.00168 |
| Haiku 4.5 | $0.00011 | $0.00084 |
Grade A, and why
content-patterns 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openEHR Specification Content Patterns
This skill captures the recurring prose patterns found across all openEHR specification
documents in the specifications-XX repositories (RM, AM, BASE, LANG, PROC, SM, QUERY,
CNF, TERM, ITS-*), derived from the existing library and its shared infrastructure in
specifications-AA_GLOBAL. Apply them when writing new chapters or sections to match the
quality and consistency of the existing specification library. They do not apply to
non-openEHR specifications or general technical documentation.
References
- Prose pattern catalog: see
references/prose-patterns.mdfor the full structure, AsciiDoc template, real example, and conventions for each pattern indexed below. - Cross-reference attribute guide: see
../authoring/references/cross-references.mdfor how to find and use{openehr_*}attributes when writing cross-references in spec prose.
General Principles
- Formal register: third person, present tense, no contractions, no hedging.
- Declarative facts first: lead with what the model defines, not how the reader should interpret it.
- Design rationale where non-obvious: explain why, not just what.
- Ground every claim: reference RM classes, archetype paths, or external standards. Never invent identifiers.
- Clinical examples: use concrete clinical scenarios to illustrate abstract model concepts.
Pattern Catalog
Pick the pattern that matches the section being written and read its detailed entry in
references/prose-patterns.md.
| # | Pattern | Use when writing… |
|---|---|---|
| 1 | Package/Chapter Overview | the opening of a chapter that describes a model package (opening paragraph → UML diagram → package/class enumeration) |
| 2 | Class/Concept Semantics | the prose for a class or major concept (purpose, typing, identification, structure, lifecycle, relationships) |
| 3 | Design Rationale | an explanation of why a non-obvious design choice was made (problem/requirement → chosen design → rejected alternatives) |
| 4 | Clinical/Practical Examples | a concrete clinical scenario that grounds an abstract model concept |
| 5 | Requirements Sections | an explicit numbered-requirements section preceding a design (common in Data Types, EHR IM) |
| 6 | Deprecated and TBD Markers | [.deprecated] or [.tbd] annotations for legacy or pending content |
| 7 | Figures and Diagrams in Context | any diagram — always introduced by text and followed by explanation |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 62 lines · 111 tokens per session scan A fe3ff33085b6
content-patterns is a skill published in the GitHub repository openEHR/ai-plugins (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 111 tokens to every session and 840 once invoked, about $0.0006 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 skills, from other repositories
project-context
Detect a repository's languages, frameworks, databases, and observability stack, then load only the relevant Magician lore cores and task-matched deep dives. Use before implementation, debugging, review, performance, database, or logging work when project-specific technical guidance would improve the result, or when…
divine
Thorough, research-grounded code review of a change, PR, or MR — multi-lens (correctness, security, simplification, tests), severity-ranked with impact + fix, configurable depth, optional PR comments. Use when asked to review code, "do a code review", "review this PR/MR", "review my changes/diff/branch", or audit a…
transmute
Comprehend an existing feature, then PORT it to another app (optionally upgrading it) or INTEGRATE/transform it in place — including swapping the vendor behind the scenes while preserving the exact UX. Use for "port/re-implement/clone this feature into ", "swap/migrate the vendor behind but keep the UX", "figure out…
confluence
Work with Confluence over its REST API (no MCP) — read/search (CQL), summarize pages, find docs, create/update/comment/label. Use for any read/search/create/update on Confluence pages, or references to a remembered space, page, or doc.
jira
Work with Jira over its REST API (no MCP) — read/search (JQL), look up tickets, my board/sprint, create/comment/@mention/transition/link/worklog, MR investigation, clone the ticket's repo. Use for any read/search/create/update/transition on Jira issues, or references to a remembered board, project, epic, or person.
knowledge-graph
Local code knowledge-graph + cache (no MCP, no network) — index a repo and retrieve ranked file:line for a topic instead of grepping whole files; show graph/cache status; blast-radius / dependents of a file; refresh or reset. Use for "knowledge graph status", "index this repo", "what depends on ", "find the code for ".