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 darellchua2/opencode-config-template --skill interactive-document-rendering-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/interactive-document-rendering-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/interactive-document-rendering-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/interactive-document-rendering-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.02202 |
| Opus 5 | $0.00026 | $0.01101 |
| Sonnet 5 | $0.00010 | $0.00440 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
interactive-document-rendering-skill 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 4d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I am the single source of truth for how document-creation skills render their Markdown sources into two complementary deliverables:
- Interactive HTML — a self-contained, navigable, dark-mode-aware web page
- Word (.docx) — a formal deliverable with auto-generated TOC and hyperlinked headers
Consumers (vision-creation-skill, srs-creation-skill, and later brd-creation-skill) reference me via "Render dual outputs per interactive-document-rendering-skill." They do NOT redefine HTML/DOCX styling themselves — that would re-introduce the inconsistency this skill exists to eliminate.
SCOPE — what I do NOT do
- No
.xlsx. Tabular artifacts (RTM, data dictionaries, requirement registers) are produced byxlsx-specialist-skill/xlsx-specialist-subagentas peer deliverables, linked from the doc — never embedded in HTML/DOCX. - No
.pptx. Customer presentation decks are produced bypptx-specialist-subagentas peer deliverables. - No image interpretation. If image content must be understood (screenshots, reference images, diagrams), delegate to
image-analyzer-subagent— do not attempt to interpret images inline.
This keeps each format's tooling owned by its specialist and the rendering skill focused on HTML + DOCX.
When to regenerate: living vs snapshot
| Doc type | HTML lifecycle | When to (re)render |
|---|---|---|
| Vision (discovery, customer) | Living — updated through the session | After each wireframe/feedback round so the client always sees current state; cheap to regenerate |
| SRS / BRD (internal) | Snapshot | Rendered once at wrap, after all sections are confirmed |
The living model applies to discovery only; internal docs render a single final snapshot.
Naming & placement
| Artifact | Path |
|---|---|
| Source Markdown | docs/{type}/{NAME}-{slug}.md (e.g. docs/vision/VISION-inventory.md, docs/srs/SRS-{key}.md) |
| Interactive HTML | docs/{type}/{slug}/{NAME}.interactive.html |
| Word deliverable | docs/{type}/{NAME}-{slug}.docx |
| Peer xlsx | docs/{type}/{slug}/{NAME}-{artifact}.xlsx (linked, not embedded) |
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.
- 4d ago First seen · 203 lines · 52 tokens per session scan A 2bd09fbe0f31
interactive-document-rendering-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 2,202 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
pdf-processing
Process and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files.
data-analysis
DuckDB-powered analytical engine for large data dumps (JSON, CSV, Parquet). Ingest → Profile → Query → File insights.
cite-sources
How to attribute every factual claim to a corpus document.
google-workspace
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via gws CLI (googleworkspace/cli). Uses OAuth2 with automatic token refresh via bridge script. Requires gws binary.
notion
Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.