report-html-writer

report-html-writer is an agent for Claude Code from cogni-work/insight-wave. It costs 116 tokens per session (2,861 once invoked), scanned A, original, Apache-2.0.

A worker agent that turns a markdown report and its enrichment plan into one self-contained HTML file. It preserves the report's prose and can include Chart.js charts, inline SVG diagrams, themed layout, and navigation when those inputs call for them.

In plain words
What is it for?
Use it to render enriched reports as standalone HTML pages, including data visualisations, concept diagrams, sidebar navigation, and validation details such as word and heading counts.
Why use it?
It provides a defined rendering step for report-enrichment workflows, with a machine-readable success or error response. It also checks whether the generated page retained the source content and requested enrichments.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cogni-workspace plugin — 18 agents shipped together

Good fit Use it to render enriched reports as standalone HTML pages, including data visualisations, concept diagrams, sidebar navigation, and validation details such as word and heading counts.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add cogni-work/insight-wave
Claude Code
/plugin install cogni-workspace

Made for: Claude Code.

Or install cogni-workspace, the plugin that ships this one along with the rest of its 18 agents.

Wrote 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.

agentmods badge for report-html-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/report-html-writer.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/report-html-writer)
Your own site
<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>
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,861 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash abd1cf06848a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

cogni-workspace/agents/report-html-writer.md · 211 lines

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

Read the full file on GitHub · 211 lines

Changes

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.

  1. 2d ago First seen · 211 lines · 116 tokens per session scan A abd1cf06848a

Subscribe to this mod's changes

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.