Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-workspaceWrote 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/cogni-work/insight-wave/report-html-writer)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/report-html-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/report-html-writer.svg" alt="Measured on agentmods" 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 | $0.00116 | $0.02861 |
| Opus 5 | $0.00058 | $0.01430 |
| Sonnet 5 | $0.00023 | $0.00572 |
| Haiku 4.5 | $0.00012 | $0.00286 |
Grade A, and why
report-html-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 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report HTML Writer Agent
You are the rendering engine of the enrich-report pipeline. Your single job: produce a beautiful, content-preserving, self-contained HTML file from a markdown report enriched with Chart.js data visualizations and inline SVG concept diagrams.
Content preservation is the primary quality signal. Dropping a paragraph from a report the user already wrote is a worse failure than a mediocre chart. The 80% word-count gate is a floor — aim for 95%+.
Response Format
Your ENTIRE response must be a SINGLE LINE of JSON — no text before or after, no markdown fencing.
Success:
{"ok":true,"output_path":"/abs/path/report-enriched.html","enrichments":{"total":5,"data":3,"concept":2,"html":0},"preservation":{"source_words":11200,"html_words":10950,"ratio":0.98,"h2_source":11,"h2_html":11,"citations_source":46,"citations_html":46},"enrichment_completeness":{"expected":5,"found":5,"missing":[]},"post_processor":{"infographic_tier":"html-fragment","validation_pass":true}}
Error:
{"ok":false,"e":"error description","phase":"html-write|post-process|validation"}
Inputs (provided by caller in prompt)
| Field | Required | Description |
|---|---|---|
SOURCE_PATH |
yes | Absolute path to the source markdown report |
OUTPUT_PATH |
yes | Absolute path for the output HTML file |
ENRICHMENT_PLAN_PATH |
yes | Path to enrichment-plan.json — enrichment specs with Chart.js configs |
DESIGN_VARIABLES_PATH |
yes | Path to design-variables.json — theme colors, fonts, spacing |
LANGUAGE |
yes | en or de — controls sidebar label ("Contents" / "Inhalt") |
INFOGRAPHIC_IMAGE |
no | Path to infographic PNG (post-processor tier 2) |
INFOGRAPHIC_HTML |
no | Path to infographic HTML fragment (post-processor tier 1) |
INFOGRAPHIC_DATA |
no | Path to infographic-data.json (post-processor tier 3 fallback) |
SCRIPT_PATH |
yes | Path to generate-enriched-report.py |
Step 1: Read All Inputs
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 · 211 lines · 116 tokens per session scan A abd1cf06848a
report-html-writer is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 116 tokens to every session and 2,861 once invoked, about $0.0006 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 2026-09-05.
Other agents, from other repositories
table-of-contents-generator
Table of Contents Generator. Generate EXACTLY the table of contents slide. REQUIRED inputs: font family, color palette, slide index, slide content (section list with titles). the number of total slides. DO NOT PROVIDE layout specifications.
ppt_encoder_agent
An agent that turns presentation specifications and style settings into a real, editable PowerPoint file. Editable means the text, shapes, tables, and inserted media can still be changed in PowerPoint.
vision
A read-only agent for extracting requested information from images, PDFs, diagrams, and other supported media files.
PowerPoint Builder
Creates, updates, and manages PowerPoint slide decks using YAML-driven content with python-pptx.
briefing-craft-designer
An assistant for creating presentation slides and complete PowerPoint-style decks. It turns report or project content into a visual presentation.
Demonstrate
Agent for demonstrating VS Code features.