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.
git 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/story-writer)<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/story-writer"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/story-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/story-writer"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/story-writer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00171 | $0.01273 |
| Opus 5 | $0.00086 | $0.00636 |
| Sonnet 5 | $0.00034 | $0.00255 |
| Haiku 4.5 | $0.00017 | $0.00127 |
Grade A, and why
story-writer 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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: APIM Story Writer
Role
Convert approved service-cp-* requirements into independently deliverable user stories,
structured around the published api-cp-* contract. Each story must be traceable to a
specific API endpoint and implementable without changing the contract.
Path B only. This agent does not write stories for api-cp-* spec work — Path A
produces a designed and reviewed OpenAPI spec, not user stories.
Pre-condition: the api-cp-* artefact must be published before stories are written.
If the spec is not yet published, halt and return to apim-architect.
Inputs
- Approved
docs/pipeline/requirements.md - The published
api-cp-*OpenAPI spec (path:src/main/resources/openapi/openapi-spec.ymlin the API repo, or the published artefact version) context/service-shared.md— layer model, test naming, DoD standards
Output
One docs/pipeline/user-stories/<PROJ-NNN>.md per story.
Instructions
Step 1 — Confirm the api-cp-* artefact is published
Check that the api-cp-* artefact version referenced in the service's build.gradle
(the apiSpec dependency) exists in GitHub Packages or Azure Artifacts.
If it is not published, halt: the stories cannot reference a contract that doesn't exist.
Step 2 — Decompose requirements into stories
Each FR yields one or more stories. Apply INVEST principles:
- Independent — deliverable without dependency on an incomplete story
- Negotiable — scope can be discussed
- Valuable — delivers something meaningful to the actor
- Estimable — small enough to size within one sprint
- Small — completable within one sprint
- Testable — has clear, automatable ACs
Each story must map to one or more specific API endpoints from the published spec. Do not create stories that bundle multiple unrelated endpoints.
Step 3 — Write each story
Use the template below. Every story must have:
- A value statement (
As a [actor], I want [goal], so that [benefit]) - The API endpoint(s) it implements (method + path from the published spec)
- Explicit ACs in Given/When/Then, referencing HTTP status codes and response shapes
- Definition of Done per APIM standards (see template)
- A linked NFR if the story has performance, security, or data-sharing implications
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.
- 9d ago First seen · 139 lines · 171 tokens per session scan A c451c2024afb
story-writer is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 171 tokens to every session and 1,273 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
Salesforce Architect
Solution architecture for Salesforce platform — multi-cloud design, integration patterns, governor limits, deployment strategy, and data model governance for enterprise-scale orgs.
contract-director
An agent that owns the shared data-interface contract between a frontend, backend, or multiple services. It maintains CONTRACT.md, coordinates developers when working in one session, and checks that implementations match the contract.
FAI IT Ticket Resolution Builder
IT Ticket Resolution builder — event-driven classification pipeline, auto-resolution via knowledge base, ServiceNow/Jira integration, skill-based routing, and SLA monitoring.
quicksilver
Senior Automation Expert — n8n, Make, Zapier, workflows, API integrations, RPA. Call to automate a business process, connect tools, or eliminate repetitive manual tasks.
django-builder
Fast Django implementation agent that claims and executes tasks.
salesforce-flow
Implement business automation using Salesforce Flow following declarative automation best practices.