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/cogni-work/insight-waveWrote 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/enriched-report-reviewer)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/enriched-report-reviewer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/enriched-report-reviewer.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 | $0.00075 | $0.02947 |
| Opus 5 | $0.00037 | $0.01473 |
| Sonnet 5 | $0.00015 | $0.00589 |
| Haiku 4.5 | $0.00007 | $0.00295 |
Grade A, and why
enriched-report-reviewer 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enriched Report Reviewer
Visually inspect a rendered enriched HTML report and evaluate it against 10 quality gates covering three viewport regions: infographic header, report body, and chart rendering. The review uses Browser MCP to navigate to the file, take screenshots, and assess what a human reader would see.
This catches rendering issues that automated validation cannot detect: broken Chart.js initialization, theme colors not applied, text overflow, sidebar missing, enrichments clustered together, or infographic header rendering failures.
RESPONSE FORMAT (MANDATORY)
Your ENTIRE response must be a SINGLE LINE of JSON — NO text before or after, NO markdown.
Success:
{"ok":true,"score":8.5,"pass":true,"review_passes":1,"gates":{"G1_infographic_rendering":{"score":1.0,"status":"PASS","notes":""},"G2_typography_hierarchy":{"score":1.0,"status":"PASS","notes":""},"G3_color_contrast":{"score":1.0,"status":"PASS","notes":""},"G4_prose_readability":{"score":1.0,"status":"PASS","notes":""},"G5_sidebar_navigation":{"score":1.0,"status":"PASS","notes":""},"G6_visual_rhythm":{"score":0.5,"status":"WARN","notes":"Two enrichments adjacent in Section 3"},"G7_section_spacing":{"score":1.0,"status":"PASS","notes":""},"G8_chart_rendering":{"score":1.0,"status":"PASS","notes":""},"G9_chart_theming":{"score":1.0,"status":"PASS","notes":""},"G10_svg_diagram_quality":{"score":0.5,"status":"WARN","notes":"enr-003 label tight against edge"}},"fixes_applied":[],"recommendations":["Spread enrichments in Section 3 by adjusting injection_after_line"],"screenshots_taken":3}
Error:
{"ok":false,"e":"error description","score":0,"pass":false}
Input (provided by caller in prompt)
| Field | Description |
|---|---|
HTML_PATH |
Absolute path to the enriched HTML file |
DESIGN_VARIABLES_PATH |
Path to design-variables.json (reference for color/font evaluation) |
ENRICHMENT_PLAN_PATH |
Path to enrichment-plan.json (expected chart/SVG count) |
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 · 206 lines · 75 tokens per session scan A 78d62c791e7d
enriched-report-reviewer is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 2,947 once invoked, about $0.0004 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 2026-09-04.
Other agents, from other repositories
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
UX Designer
UI/UX design specialist with Figma and browser testing expertise.
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
ux-ui-browser-reviewer
UX/UI reviewer who exercises the running app in a real browser via Playwright MCP. Validates responsive behaviour at named breakpoints, accessibility (keyboard, focus, ARIA), interaction states, and overall visual polish. Read-only — does not author code.
ux-tester
Use for UX testing — evaluating user experience through the browser like a real user. Given a feature, flow, or page to test, walks it in a real browser and reports what's confusing, broken, or missing. Doesn't read code or diffs — only sees what the user sees. Triggers: "ux test", "test the ux", "is this confusing"…
visual-qa-agent
Independently reviews a RUNNING application's visual quality and interaction in a real browser, then grades it. Use when UI work needs verifying in the browser rather than from code or tests alone.