hmcts-apim-sdlc-orchestrator

hmcts-apim-sdlc-orchestrator is a plugin for Claude Code from hmcts/agentic-plugins-marketplace. Its manifest loads nothing; the 9 skills, 12 agents, 3 hooks it bundles cost 3,638 tokens per session together, scanned A, original, MIT.

A workflow coordinator for building and releasing APIs, which are interfaces that let software systems communicate. It uses API descriptions written in OpenAPI, a standard format for documenting those interfaces, and Spring Boot services, a Java framework for building web services.

In plain words
What is it for?
Use it to create API specifications and Spring Boot services, check compatibility and examples, prepare repositories, wire up deployment checks, audit feature flags, and publish eligible APIs.
Why use it?
It organizes the steps from requirements and API design through coding, testing, review, deployment, and catalogue publishing, reducing gaps between those stages.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit Use it to create API specifications and Spring Boot services, check compatibility and examples, prepare repositories, wire up deployment checks, audit feature flags, and publish eligible APIs.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add hmcts/agentic-plugins-marketplace/plugin install hmcts-apim-sdlc-orchestrator
Install

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.

Clone the repo
git clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplace

Made for: Claude Code.

Wrote 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.

agentmods badge for hmcts-apim-sdlc-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/plugins/hmcts/agentic-plugins-marketplace/hmcts-apim-sdlc-orchestrator.svg)](https://agentmods.dev/plugins/hmcts/agentic-plugins-marketplace/hmcts-apim-sdlc-orchestrator)
Your own site
<a href="https://agentmods.dev/plugins/hmcts/agentic-plugins-marketplace/hmcts-apim-sdlc-orchestrator"><img src="https://agentmods.dev/badge/plugins/hmcts/agentic-plugins-marketplace/hmcts-apim-sdlc-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 9 skills, 12 agents, 3 hooks cost 3,638 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

hmcts-apim-sdlc-orchestrator 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 yesterday.

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.

plugins/agents/hmcts-apim-sdlc-orchestrator/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "name": "hmcts-apim-sdlc-orchestrator",
  "version": "1.5.0",
  "description": "HMCTS API-Marketplace SDLC orchestrator — a fully self-contained, contract-first pipeline for OpenAPI-first api-cp-* spec libraries and service-cp-* Spring Boot services. Bundles all pipeline agents (requirements-analyst, apim-architect, story-writer, contract-test-engineer, implementation, code-reviewer, amp-security, ci-orchestrator, deployer, catalog-publisher) plus two hub-and-spoke specialists (contract-compatibility-analyzer, feature-flag-auditor), the openapi-spec-reviewer, entra-token-validation, bootstrap-context, and release skills, the forked springboot-api-from-template / springboot-service-from-template repo-bootstrap skills (with git-access verification and README-hygiene trimming of template boilerplate), the wire-service-deployment CI-wiring skill now chained to a new exclude-db-from-priming-clear skill (protects any service-cp-*-owned database from the nonprod priming pipeline's quick_clear sweep), APIM context docs (including a standardized ClockService time-access pattern), and guard hooks. catalog-publisher runs a mandatory eligibility check and validates OpenAPI examples against their schemas before registering. Every pipeline stage now states an explicit signal/handoff to the next agent, implementation enforces a physical red-test gate before any code is written, and the Hard rules carry a broadened, enumerated ADR-trigger list. Targets GHA + ADO CI/CD, PMD, CodeQL, GHCR, and the cp-vp-aks-deploy GitOps repo.",
  "author": {
    "name": "HMCTS APIM"
  },
  "license": "MIT",
  "keywords": [
    "hmcts",
    "apim",
    "api-marketplace",
    "sdlc",
    "orchestrator",
    "openapi",
    "spring-boot",
    "contract-first",
    "agents",
    "pipeline",
    "jwt",
    "entra",
    "security"
  ]
}
Changes

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.

  1. yesterday Changed · +3 lines e22b0155706a
  2. 8d ago First seen · 21 lines scan A d935d9a815df

Subscribe to this mod's changes

hmcts-apim-sdlc-orchestrator is a plugin published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.