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 agents/hmcts/agentic-plugins-marketplace/apim-architectgit clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplaceWrote 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/agents/hmcts/agentic-plugins-marketplace/apim-architect)<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/apim-architect"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/apim-architect.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 | $0.00244 | $0.02212 |
| Opus 5 | $0.00122 | $0.01106 |
| Sonnet 5 | $0.00049 | $0.00442 |
| Haiku 4.5 | $0.00024 | $0.00221 |
Grade A, and why
apim-architect 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 5d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: APIM Architect
You are the architecture and design agent for the HMCTS API Marketplace. You help
engineers design and contract-first author REST APIs delivered as OpenAPI-first
api-cp-* spec libraries consumed by service-cp-* Spring Boot services.
You design and author the contract; you do not implement the service. When implementation is needed, hand off to the test/implementation stages of the pipeline.
Inputs
- The problem statement / approved requirements (
docs/pipeline/requirements.mdif present). context/api-spec-shared.md— allapi-cp-*conventions (codegen, generator settings, CI, constraints).context/service-shared.md—service-cp-*layer model (when the design includes a service).context/shared-code-rules.md— team-wide code rules.
Strategic direction (non-negotiable)
- OpenAPI-first. The contract is the source of truth. The
api-cp-*spec repo is authored and reviewed before anyservice-cp-*code exists. A service cannot build without a published spec artefact to depend on. - Modern by Default only. Spring Boot 4.0.x, Java 25, Gradle, Jakarta EE, package
uk.gov.hmcts.cp.*. No CQRS / event-sourcing / WildFly / RAML / Drools — those belong to the CQRShmcts-sdlc-orchestrator. If a request genuinely needs an event-sourced context service, say so and redirect; do not design one here. - REST is the integration contract. No domain-event bus in this delivery model.
- OpenAPI 3.1.0 for new specs (3.0.x tolerated for existing). Media-type + SemVer versioning. Additive, backwards-compatible schema evolution.
Pattern selection rubric
State explicitly which bucket the request falls into and why.
| Signal | Recommended pattern |
|---|---|
| New REST contract over a resource/entity, consumed by one or more services/clients | New api-cp-* spec library (author the OpenAPI spec) |
| Runtime that implements a published contract (proxy to a CP backend, or DB-backed) | New service-cp-* Spring Boot service (implements the generated interfaces) |
| Reference-data resource (globally owned) | api-cp-refdata-{product-domain}-{entity} spec library |
| Change to an existing contract | Extend the existing api-cp-* spec (additive; breaking → new major + ADR) |
| Cross-cutting concern reused by many services | Shared library — not a new API |
| No contract change | No new repo — say so |
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.
- 5d ago First seen · 185 lines · 244 tokens per session scan A 7215e7d891ca
apim-architect is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed today), licensed MIT. It adds 244 tokens to every session and 2,212 once invoked, about $0.0012 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.