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 skills/teimurjan/blazediff/image-comparenpx skills add teimurjan/blazediff --skill image-comparegit clone --depth 1 https://github.com/teimurjan/blazediffWrote 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/teimurjan/blazediff/image-compare)<a href="https://agentmods.dev/skills/teimurjan/blazediff/image-compare"><img src="https://agentmods.dev/badge/skills/teimurjan/blazediff/image-compare.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 | $0.00049 | $0.02376 |
| Opus 5 | $0.00024 | $0.01188 |
| Sonnet 5 | $0.00010 | $0.00475 |
| Haiku 4.5 | $0.00005 | $0.00238 |
Grade A, and why
image-compare 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 5d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-compare
Two image files in, a verdict out. No baselines, no manifest, no browser.
CLI binary is blazediff-cli (npm i -g @blazediff/cli).
Not this skill: capturing a running app, managing baselines, or re-running a
visual regression suite → use the blazediff skill instead (it owns
.blazediff/, blazediff-agent, and the check/rewrite loop). If the working
directory has a .blazediff/manifest.json and the user is asking about routes
rather than files, you are in the wrong skill.
Be terse
- Pass
--jsonon every call; parse fields. Do not echo CLI output. - Never send whole images to a model when
interprethas located the regions — see Send crops, not pages below. This is the point of the skill. - One final summary line:
N regions | <severity> | <one-clause verdict>.
Pick the command by the question
| The user is asking | Command | Read from it |
|---|---|---|
| "what changed?" / "describe the differences" | interpret |
regions[] — bbox, changeType, position |
| "are these identical?" | core-native |
different pixels (0 = byte-identical after decode) |
| "how different, perceptually?" | ssim |
SSIM score, 1.0 = identical |
| "did quality degrade?" (compression, resize, generative output) | msssim |
multi-scale score, 1.0 = identical |
| "where are the structural differences?" | gmsd -o map.png |
deviation, 0.0 = identical |
interpret is the default. The others answer how much; only interpret
answers what.
blazediff-cli interpret a.png b.png --json
Exit codes: 0 no regions, 1 regions found, 2 error. Safe to branch on.
Picking --source
pixel(default) — pixel-aligned renders: screenshots, PNG exports, chart renders, PDF rasterizations. Anything produced twice by the same renderer.ms-ssim/ssim— images with resampling or compression noise: JPEGs, camera captures, generative-model output, anything that went through a lossy round-trip. Per-pixel deltas are everywhere in these, sopixelreturns one giant region; the metric sources threshold a similarity map instead. Their boxes are coarser (map-grid resolution), but the pixel counts inside them are still exact.
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.
- 5d ago First seen · 184 lines · 49 tokens per session scan A 63a604644508
image-compare is a skill published in the GitHub repository teimurjan/blazediff (338 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 2,376 once invoked, about $0.0002 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 skills, from other repositories
visual-qa-testing
Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors, and auditing network requests. Use after making UI changes to verify they look correct.
playwright-scanner
Internal helper for behavioral accessibility testing using Playwright. Runs keyboard navigation scans, dynamic state scans, viewport responsive scans, contrast verification, and accessibility tree snapshots against live pages. Read-only -- never modifies files.
review-screenshot
統一截圖入口。Use when 使用者要求截圖驗證 UI 畫面，或要跑 UI 檢查清單。NOT for 把既有截圖 sweep 進 archive/（走 screenshots-archive），NOT for Lighthouse 稽核或 performance trace 拆解（走 chrome-devtools-mcp）。.
visual-regression-lab
Use after frontend changes or before delivery to run rendered visual QA with Playwright/browser screenshots, viewport checks, console/network checks, overflow detection, canvas/media verification, before/after comparisons, and responsive polish review.
create-or-update-pr
Create a pull request for the current branch, or update the existing one if it already exists. Regenerates the title (Conventional Commits format) and the body (Objective + What was done) from the actual changes, in English. INVOKE when the user asks to "open a PR", "create a PR", "update the PR", "update PR…
visual-qa-vision-agent
Equips the AI agent with visual QA capabilities using Playwright/Puppeteer and the agent's innate Vision capabilities to self-correct UI layout, CSS alignment, and visual regressions.