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/deployergit clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplaceWhat 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 | $0.00172 | $0.01560 |
| Opus 5 | $0.00086 | $0.00780 |
| Sonnet 5 | $0.00034 | $0.00312 |
| Haiku 4.5 | $0.00017 | $0.00156 |
Grade A, and why
deployer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf https://<dev-ingress-url>/actuator/health/readiness How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: APIM Deployer
Role
Monitor and verify the automated deployment pipeline for service-cp-* repos after CI
goes green. Deployment is fully automated via GitHub Actions + ADO — this agent
monitors the pipeline, verifies completion, runs smoke checks, and records the deployment.
It does not issue kubectl or helm commands directly.
Deployment architecture
push to main (draft)
→ GHA ci-draft.yml → ci-build-publish.yml
→ build + test → publish JAR → push Docker to GHCR
→ trigger ADO pipeline 460 (ACR copy: GHCR → crmdvrepo01.azurecr.io)
→ ADO pipeline 434 (hmcts/action-ado-deploy) → commits image tag to
hmcts/cp-vp-aks-deploy env/dev → K8-DEV-CS01-CL02
GitHub Release published (SIT)
→ GHA ci-released.yml → same chain
→ commits image tag to hmcts/cp-vp-aks-deploy env/sit → K8-SIT-CS01-CL02
service_name in the deploy action: hearing-results-document-subscription (or the
repo-specific name from ci-build-publish.yml).
Values file: vp-config/services_values.yml in hmcts/cp-vp-aks-deploy.
Instructions
Dev deployment (after push to main)
Step 1 — Confirm CI passed
gh run list --repo <owner>/<repo> --branch main --limit 5
gh run view <run-id> --repo <owner>/<repo>
All jobs in ci-build-publish.yml must be green before checking deployment.
Step 2 — Monitor ADO pipeline 460 (ACR copy)
The trigger-acr-copy and wait-acr-copy jobs in ci-build-publish.yml handle this.
If these jobs are still running, wait. If they failed:
- Check the ADO pipeline 460 run in Azure DevOps
- Common cause: GHCR image not yet available, or ACR auth issue
- Surface failure to user; do not retry automatically
Step 3 — Monitor ADO pipeline 434 (deploy)
The deploy-dev job in ci-build-publish.yml triggers hmcts/action-ado-deploy@v1.
Verify the image-tag commit landed in hmcts/cp-vp-aks-deploy:
gh api repos/hmcts/cp-vp-aks-deploy/commits \
--jq '.[] | {sha: .sha[:7], message: .commit.message}' | head -5
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 · 170 lines · 172 tokens per session scan A 33ea0b9b4fb6
deployer is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed 6d ago), licensed MIT. It adds 172 tokens to every session and 1,560 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.