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 xAmirHamza77/ReverseOps-Skill --skill screenshotsgit clone --depth 1 https://github.com/xAmirHamza77/ReverseOps-SkillWrote 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/xamirhamza77/reverseops-skill/screenshots)<a href="https://agentmods.dev/skills/xamirhamza77/reverseops-skill/screenshots"><img src="https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/screenshots/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/xamirhamza77/reverseops-skill/screenshots"><img src="https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/screenshots.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 | $0.00052 | $0.06094 |
| Opus 5.5 | $0.00021 | $0.02438 |
| Sonnet 5.5 | $0.00010 | $0.01219 |
| Haiku 4.5 | $0.00005 | $0.00609 |
Grade A, and why
screenshots 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 1mo 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 — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshots Skill (advanced mode)
Version: 2.0 (Single-file mode) | Backend: Resolution-agnostic, uses pure pixel coordinates (pixels) | Focus: Advanced reasoning and problem solving
CRITICAL: Microscope model (not primary analysis)
This skill is a microscope, not a primary analysis tool. It is Powerful for deep analysis, but Expensive (slow, high token usage). It Supports UI Mapper (the primary inspection tool).
Key Principles:
- Less is More. Use it SPARINGLY, NOT by default.
- Flat Architecture. Analyze in a single pass; NO recursive decomposition.
- UI has no recursive structure. Do not invent hierarchy where none exists.
- Element Count Match. MUST match the pixel/reference image as closely as possible.
- Fail Fast. If inspection fails after 1 retry, STOP and show the error.
- No Features. Do not document features/behaviors; ONLY report what you can SEE.
- Debug-First. Focus on malformed inputs, pollution, and state mismatches.
- Advanced Analysis. Here for complex analysis, not your FIRST analysis attempt.
- Evidence Based. Do not guess/hallucinate; base everything on observable evidence.
- Pixel-Perfect ROI. Validate element sizes through actual screenshot regions, NOT via uamappings alone (accuracy gate).
CRITICAL: Data freshness (non-negotiable)
- Inventory Data MUST be < 30 seconds old. If
since_capture> 30s, RE-CAPTURE. - Screenshots MUST be from the CURRENT session (after the last capture/screenshot command).
- NEVER reuse uamappings across contextual changes (app switch, navigate, resize, session change).
- Changing target app invalidates prior inventory data (target_mismatch).
- After device capture, ALWAYS wait 300–500ms before screenshot ROI processing.
- NEVER assume the UI is static; verify with a fresh capture if unsure.
- If the map is Stale, RE-CAPTURE (fresh screenshot +
uiauto inventory + map) before proceeding.
CRITICAL: Screenshot performance (keep files small)
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.
- 1mo ago First seen · 642 lines · 52 tokens per session scan A 87423c0adae1
screenshots is a skill published in the GitHub repository xAmirHamza77/ReverseOps-Skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 6,094 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
fix-my-app
Find and fix a problem in a Taskade Genesis app, change one thing at a time, and prove the change with the file contents. Use when the user says "my Taskade app is broken", "fix my app", "the page is blank", "the button does nothing", "data does not show in my app", or asks to change text, layout or a field in their…
interacting-with-project-runtime
Interacting with a project's JVM runtime through the Kotlin REPL to execute focused probes against project classes and dependencies. Activate when behavior must be observed by running code; use using-gradle for build inspection or task execution.
using-gradle
Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.
browser-debug
Debug style issues and console errors in a running web app using the kogiQA browser tools. Use when asked to investigate a layout/overflow problem, a broken page, or to collect and fix console errors.
debug-helper
Systematic debugging approach for identifying and fixing issues.
error-handling
Read the error codes these tools raise and decide whether to retry, fix the call, or stop.