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/boshi-xixixi/traeskill/eyeballnpx skills add boshi-xixixi/TraeSkill --skill eyeballgit clone --depth 1 https://github.com/boshi-xixixi/TraeSkillWrote 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/boshi-xixixi/traeskill/eyeball)<a href="https://agentmods.dev/skills/boshi-xixixi/traeskill/eyeball"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/eyeball.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 | $0.00050 | $0.01483 |
| Opus 5 | $0.00025 | $0.00741 |
| Sonnet 5 | $0.00010 | $0.00297 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
eyeball 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eyeball
Analyze documents with visual proof. When activated, Eyeball produces a Word document on the user's Desktop where every factual assertion includes an inline screenshot from the source material with the cited text highlighted in yellow.
Activation
When the user invokes this skill (e.g., "use eyeball", "run eyeball on this", "eyeball this document"), respond with:
Eyeball is active. I'll analyze the document and produce a Word doc with inline source screenshots so you can verify every claim with your own eyes.
Then follow the workflow below.
Supported Sources
- Local files: Word documents (.docx, .doc), PDFs (.pdf), RTF files
- Web URLs: Any publicly accessible web page
Tool Location
The Eyeball Python utility is located at:
<plugin_dir>/skills/eyeball/tools/eyeball.py
To find the actual path, run:
find ~/.copilot/installed-plugins -name "eyeball.py" -path "*/eyeball/*" 2>/dev/null
If not found there, check the project directory or the user's home directory for the eyeball repo.
First-Run Setup
Before first use, check that dependencies are installed:
python3 <path-to>/eyeball.py setup-check
If anything is missing, install the required dependencies:
pip3 install pymupdf pillow python-docx playwright
python3 -m playwright install chromium
On Windows, also install pywin32 for Word automation:
pip install pywin32
Workflow
Follow these steps exactly. The order matters.
Step 1: Read the source text
Before writing any analysis, extract and read the full text of the source document:
python3 <path-to>/eyeball.py extract-text --source "<path-or-url>"
Read the output carefully. Identify actual section numbers, headings, page numbers, and key language.
CRITICAL: Do not skip this step. Do not write analysis based on assumptions about how the document is structured. Read the actual text.
Step 2: Write analysis with exact citations
For each point in your analysis, you must:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 171 lines · 50 tokens per session scan A 4f9d6460e4a6
eyeball is a skill published in the GitHub repository boshi-xixixi/TraeSkill (261 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 1,483 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA aud.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
resilient-context-extraction
Ensures agents extract data from context files with validation and fallback strategies before resorting to assumptions or external searches.
moai-docs-generation
Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.
report-generation
Creating structured PDF reports from data, templates, and AI-generated content using professional toolchains.
graphic-ebook
Creates professionally designed B2B SaaS e-books in HTML + CSS, exported as print-ready PDF. 3–10 pages, 9 style presets, 11 page layout types. Trigger when user says "create an ebook", "design a lead magnet", "make a PDF guide", "build a gated content piece", "write a B2B ebook", "design a white paper", "create a…