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 skills add alexmond/alexmskills --skill screenshot-sweepgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/screenshot-sweep)<a href="https://agentmods.dev/skills/alexmond/alexmskills/screenshot-sweep"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/screenshot-sweep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alexmond/alexmskills/screenshot-sweep"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/screenshot-sweep.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00128 | $0.01999 |
| Opus 5 | $0.00064 | $0.01000 |
| Sonnet 5 | $0.00026 | $0.00400 |
| Haiku 4.5 | $0.00013 | $0.00200 |
Grade A, and why
screenshot-sweep 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 7d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot sweep
Not
screenshot-tour, which produces a presentation deck of a product. This one audits a capture you already have, for defects.
A screenshot is a free full-page audit that most people spend on one bug.
You were sent the image to look at one thing. Look at everything, because the cost of the extra look is seconds and the cost of missing it is that the user finds it later and reports it — which is strictly more expensive for them than for you.
The rule
One screenshot, one sweep, then answer the question you were asked.
Do the sweep first. If you answer the question first you will stop looking, and the sweep will not happen.
Anything you find that is not what you were asked about:
- File it. A real defect with a real symptom gets an issue, with the evidence you can see and — where you can get it — the measurement behind it.
- Add it to the todo list, so it survives the conversation.
- Do not fix it now unless it is a one-liner adjacent to the work in hand. Scope creep in a bug fix is its own defect. Say what you found and move on.
Do NOT file:
- Things you suspect but cannot see in the image. "This might be slow" is not a screenshot finding.
- Aesthetic preferences. "I would have used more padding" is not a defect.
- The same thing twice — check open issues first.
The checklist
Run every line against every screenshot. Most will be "fine" in a second.
Legibility
- Any text you have to work to read? Low-contrast text on a tinted or coloured background is the classic. Measure before claiming — see "measure, don't eyeball" below.
- Text on a background of the same family (dark on dark, light on light) — usually a colour that was set for one theme and inherited into the other.
- Prose stretched to a very long line. Over ~90 characters is uncomfortable; over ~200 is a defect.
Reachability
- Controls pushed off the edge — check the top-right corner especially, where close/expand/overflow buttons live and where a long title shoves them.
- Content cut off at a container edge with no visible way to scroll to it.
- Anything clipped, overlapping, or drawn on top of something else.
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.
- 7d ago First seen · 176 lines · 128 tokens per session scan A d187d7304741
screenshot-sweep is a skill published in the GitHub repository alexmond/alexmskills (6 stars, last pushed today), licensed MIT. It adds 128 tokens to every session and 1,999 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 skills, from other repositories
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
flowchart-creator
Create HTML flowcharts and process diagrams with decision trees, color-coded stages, arrows, and swimlanes. Use when users request flowcharts, process diagrams, workflow visualizations, or decision trees.
architecture-diagram-creator
Create comprehensive HTML architecture diagrams showing data flows, business objectives, features, technical architecture, and deployment. Use when users request system architecture, project documentation, high-level overviews, or technical specifications.
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.