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 skills add hmcts/agentic-plugins-marketplace --skill export-design-artifactgit 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/skills/hmcts/agentic-plugins-marketplace/export-design-artifact)<a href="https://agentmods.dev/skills/hmcts/agentic-plugins-marketplace/export-design-artifact"><img src="https://agentmods.dev/badge/skills/hmcts/agentic-plugins-marketplace/export-design-artifact/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/skills/hmcts/agentic-plugins-marketplace/export-design-artifact"><img src="https://agentmods.dev/badge/skills/hmcts/agentic-plugins-marketplace/export-design-artifact.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 | $0.00274 | $0.01451 |
| Opus 5 | $0.00137 | $0.00726 |
| Sonnet 5 | $0.00055 | $0.00290 |
| Haiku 4.5 | $0.00027 | $0.00145 |
Grade A, and why
export-design-artifact 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Export Design Artifact
Turn a pipeline decision, plan, design gap, or comparison into a self-contained HTML artifact built from a vetted template. Every CPP pipeline stage uses this skill instead of describing a plan/decision only in chat — the artifact is the durable, reviewable record.
This is a shared skill: the architecture-designer, requirements-analyst, story-writer and implementation agents all call it. It owns one job — pick the right template and produce the file.
When you MUST export an artifact
- Before implementation (mandatory). An implementation-plan artifact (template
03) MUST exist and be surfaced at the Stage 4 human gate before Stage 5 (Code) begins — even when the design is clean and nothing is contentious. No plan artifact → do not start coding. - A decision needs to be made — any fork with consequences (pattern choice, new-vs-extend endpoint, schema shape, threshold). Export a decision record / comparison.
- A plan needs improving — when review, a gate, or new information changes the plan, re-export the updated plan artifact (same file, bump the version in the marker).
- A design gap is discovered — a missing contract, an unhandled failure mode, an ownership ambiguity. Capture it (architecture blueprint or investigation dossier) and surface it; do not silently proceed.
Exporting an artifact never replaces the human gate — it is what the human reviews at the gate.
Pick the template
The gallery lives in templates/ (bundled with this skill). Full selection guide:
templates/README.md. Visual index: templates/index.html.
| Scenario | Template file | kind= |
|---|---|---|
| Implementation / delivery plan (the mandatory pre-code artifact) | 03-implementation-plan-roadmap.html |
report |
| Decision, 3+ options or weighted | 07-decision-record-adr.html |
report |
| Decision, exactly 2 options (trade-off) | 10-comparison-versus.html |
report |
| Design gap / system structure (drawing the architecture) | 08-architecture-blueprint.html |
report |
| Design gap found via debugging / RCA (evidence → hypothesis) | 04-investigation-dossier.html |
investigation |
| Event / API sequence (order of messages across services) | 11-event-flow-signal-trace.html |
report |
| User / process flow (a human walks through it) | 05-journey-flow-swimlane.html |
report |
| Migration / reversible cutover (gates + rollback) | 06-migration-runbook.html |
report |
| Status / progress dashboard | 09-status-mission-control.html |
dashboard |
| Teaching a concept | 02-concept-explainer-aurora.html |
report |
| PR review / code audit | 01-pr-review-audit-console.html |
report |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- templates/01-pr-review-audit-console.html 9.3 KB
- templates/02-concept-explainer-aurora.html 8.3 KB
- templates/03-implementation-plan-roadmap.html 8.5 KB
- templates/04-investigation-dossier.html 7.6 KB
- templates/05-journey-flow-swimlane.html 7.8 KB
- templates/06-migration-runbook.html 8.4 KB
- templates/07-decision-record-adr.html 9.2 KB
- templates/08-architecture-blueprint.html 9.2 KB
- templates/09-status-mission-control.html 7.7 KB
- templates/10-comparison-versus.html 6.2 KB
- templates/11-event-flow-signal-trace.html 7.7 KB
- templates/index.html 16 KB
- templates/playground-skills.html 21 KB
- templates/README.md 4.5 KB
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 · 104 lines · 274 tokens per session scan A 13979cb28fd7
export-design-artifact is a skill published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed today), licensed MIT. It adds 274 tokens to every session and 1,451 once invoked, about $0.0014 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.