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/jin-bo/agentao/ocrnpx skills add jin-bo/agentao --skill ocrgit clone --depth 1 https://github.com/jin-bo/agentaoWhat 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 | $0.00099 | $0.00524 |
| Opus 5 | $0.00049 | $0.00262 |
| Sonnet 5 | $0.00020 | $0.00105 |
| Haiku 4.5 | $0.00010 | $0.00052 |
Grade A, and why
ocr 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.
What it actually says
OCR Skill
Extract text from images using scripts/ocr.py (Qwen VL OCR model).
Path note: this skill's files live in the directory containing this
SKILL.md — written as <skill-dir> below. It is shown on the
Skill directory: line when the skill is activated (the activation message
also lists the script's absolute path). The script is at
<skill-dir>/scripts/ocr.py, NOT in your current working directory.
Prerequisites
QWEN_API_KEY and QWEN_BASE_URL, read in this order (first found wins):
- process environment variables
.envin your current working directory<skill-dir>/.env(recommended place to keep them)~/.env(user-wide fallback)
QWEN_API_KEY=your_key
QWEN_BASE_URL=https://your-base-url
No dependency setup needed: the script carries inline metadata (PEP 723), so
uv run resolves openai / python-dotenv automatically in any directory.
Do NOT run uv add — your cwd is usually not a Python project.
Usage
uv run "<skill-dir>/scripts/ocr.py" <image_file>
Substitute <skill-dir> with the absolute skill directory before running —
it is NOT a shell variable. Output is printed to stdout. If credentials are missing, the script exits
with an error telling you where to put them.
Workflow
- Confirm the image file path with the user if not provided
- Run the script with the image path
- Present the extracted text to the user
- If the user wants to save the output, write it to a
.txtfile
Notes
- Blurry or overexposed single characters are replaced with
? - Supported formats:
.jpg.jpeg.png.gif.webp
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 · 55 lines · 99 tokens per session scan A 9281ecdfb305
ocr is a skill published in the GitHub repository jin-bo/agentao (95 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 524 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…