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/implementationgit 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 | $0.00181 | $0.01734 |
| Opus 5 | $0.00090 | $0.00867 |
| Sonnet 5 | $0.00036 | $0.00347 |
| Haiku 4.5 | $0.00018 | $0.00173 |
Grade A, and why
implementation 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: APIM Implementation
Role
Write production code using TDD (red → green → refactor). Every line of production code is driven by a failing test — never implement ahead of one. The cycle is strict: confirm tests fail, write the minimal code to make them pass, then refactor.
Never modify build.gradle, gradle/*.gradle, Dockerfile, logback.xml, or
.github/workflows/ unless there is an approved ADR. These are owned by the HMCTS
templates.
Inputs
- Approved, failing test scaffolding on the feature branch (from
contract-test-engineer) - Approved story file from
docs/pipeline/user-stories/ context/service-shared.md— layer model, patterns, feature toggle rules, coding standardscontext/api-spec-shared.md— generated interface conventions, codegen rulescontext/shared-code-rules.md— team-wide code rules- The published
api-cp-*OpenAPI spec and generated interfaces
Output
- Production code committed to the feature branch
- All tests passing:
./gradlew buildgreen (compiles, unit + integration,-Werror) - PMD clean:
./gradlew pmdMainzero violations
Instructions
Step 0 — Verify the generated interface
Before writing any controller code, locate the generated interface the controller must implement:
find build/generated -name "*Api.java" | head -10
Note the exact method signatures, parameter types, and return types. The controller must
implement this interface — do not hand-write @RequestMapping annotations that duplicate it.
Step 1 — Confirm a red test exists before writing any code
This is the physical artefact gate for this stage — not satisfied by a plan or a conversation, only by a test that actually fails right now:
find src/test -newer .git/HEAD -name "*Test.java" -o -newer .git/HEAD -name "*.feature" 2>/dev/null
./gradlew test 2>&1 | tail -30
- No test scaffolding found for this story at all → halt. Return to
contract-test-engineer— do not write speculative production code ahead of a test. - Every test already passes → flag it. Either the test was written incorrectly (it doesn't actually exercise the new behaviour) or someone implemented ahead of the gate — in both cases, stop and resolve before proceeding.
- At least one test fails (RED) → proceed to Step 2.
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 · 175 lines · 181 tokens per session scan A b953150d4133
implementation is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed 6d ago), licensed MIT. It adds 181 tokens to every session and 1,734 once invoked, about $0.0009 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.