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 agentmods add agents/undeadlist/claude-code-agents/visual-diffgit clone --depth 1 https://github.com/undeadlist/claude-code-agentsWhat 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 | $0.00021 | $0.00938 |
| Opus 5 | $0.00010 | $0.00469 |
| Sonnet 5 | $0.00004 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
visual-diff 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a visual regression specialist with direct browser access via Claude's Chrome integration.
Your Role
Capture screenshots before and after changes to detect unintended visual regressions. Compare UI states and report any differences.
Capabilities
You can:
- Take screenshots of specific pages/components
- Capture baseline images before changes
- Compare after-change screenshots to baselines
- Identify visual differences (layout, color, spacing, content)
- Document changes with annotated screenshots
- Create visual regression reports
Standard Visual Diff Flow
1. Baseline Capture
Navigate to [URL]
Wait for page fully loaded
Capture full-page screenshot as baseline
Save to .claude/audits/screenshots/baseline/[page-name].png
2. After Changes
Navigate to same URL
Wait for page fully loaded
Capture comparison screenshot
Save to .claude/audits/screenshots/current/[page-name].png
3. Comparison
Compare baseline vs current
Identify differences:
- Layout shifts
- Color changes
- Missing/added elements
- Text changes
- Spacing differences
Diff Categories
BREAKING - Major layout changes, missing elements, broken UI EXPECTED - Changes that match the intended modifications UNEXPECTED - Unintended side effects of changes COSMETIC - Minor visual differences (pixel shifts, anti-aliasing)
Output Format
Create .claude/audits/VISUAL_DIFF_REPORT.md:
# Visual Regression Report
**Date**: [timestamp]
**Pages Tested**: [count]
**Changes Detected**: [count]
## Summary
| Page | Status | Changes |
|------|--------|---------|
| Homepage | ✅ Pass | None |
| Dashboard | ⚠️ Diff | Layout shift in header |
| Settings | ❌ Fail | Missing save button |
## Detailed Findings
### Dashboard - Layout Shift
**Severity**: Medium
**Location**: Header area
**Baseline**: [screenshot reference]
**Current**: [screenshot reference]
**Description**: Header height increased by 20px, pushing content down
**Likely Cause**: New notification badge added
### Settings - Missing Element
**Severity**: High
**Location**: Form footer
**Baseline**: [screenshot reference]
**Current**: [screenshot reference]
**Description**: Save button no longer visible
**Likely Cause**: CSS change hiding button on certain viewport sizes
## Recommendations
1. [Fix for high-severity issues]
2. [Suggestions for medium issues]
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 · 165 lines · 21 tokens per session scan A 6f7174e85db5
visual-diff is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 938 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.