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 phanghonghao/THU-Awesome-Skills --skill img-readergit clone --depth 1 https://github.com/phanghonghao/THU-Awesome-SkillsWrote 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/phanghonghao/thu-awesome-skills/img-reader)<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/img-reader"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/img-reader/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/phanghonghao/thu-awesome-skills/img-reader"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/img-reader.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 | $0.00106 | $0.01580 |
| Opus 5 | $0.00053 | $0.00790 |
| Sonnet 5 | $0.00021 | $0.00316 |
| Haiku 4.5 | $0.00011 | $0.00158 |
Grade A, and why
img-reader 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 10d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Img-Reader - 本地图片读取(零 MCP 额度)
3 级自动降级流程
Tier 0: Read + PIL 增强(零依赖,已集成)
│ 置信度低 ↓ 自动降级
Tier 1: GLM-4V-Flash(免费 API,联网,不消耗 MCP 额度)
│ 联网失败 / 无 API Key ↓ 自动降级
Tier 2: PaddleOCR(离线,本地 OCR)
│
└──→ 输出结果(跑通即停,不浪费后续资源)
核心规则:只要上一级跑通就停,失败才自动降级。不调用 MCP analyze_image。
Tier 0: Read + PIL 增强
普通模式(截图/照片/整体描述)
直接 Read:
Read(file_path="<absolute_path>")
增强模式(工程图/明细表/小字)
用 PIL 裁剪+放大+增强后再 Read:
PYTHONIOENCODING=utf-8 python -c "
from PIL import Image, ImageEnhance, ImageFilter
import sys, os
img_path = sys.argv[1]
zoom = int(sys.argv[2]) if len(sys.argv) > 2 else 5
region = sys.argv[3] if len(sys.argv) > 3 else None
img = Image.open(img_path).convert('RGB')
w, h = img.size
if region:
coords = [float(x) for x in region.split(',')]
img = img.crop((int(w*coords[0]), int(h*coords[1]), int(w*coords[2]), int(h*coords[3])))
out = img.resize((img.width * zoom, img.height * zoom), Image.LANCZOS)
out = out.filter(ImageFilter.SHARPEN)
out = ImageEnhance.Contrast(out).enhance(1.8)
out = ImageEnhance.Sharpness(out).enhance(2.0)
base = os.path.splitext(img_path)[0]
save_path = base + '_enhanced.png'
out.save(save_path)
print(save_path)
" "<INPUT_PATH>" "<ZOOM>" "<REGION>"
置信度判断
读取后评估:
- 高:文字清晰,直接输出
[置信度:高] - 中:部分模糊,用
(?)标记不确定项[置信度:中] - 低:大量不可辨 → 自动降级到 Tier 1,不问用户
Tier 1: GLM-4V-Flash(免费 VLM API)
当 Tier 0 置信度低时,自动调用(不问用户):
python "<LOCAL_USER>/.claude/skills/img-reader/vision_api.py" "<image_path>" "<prompt>"
前提:需要 ZHIPU_API_KEY 环境变量(免费注册 https://open.bigmodel.cn 获取)
API Key 配置(三选一)
- 环境变量:
set ZHIPU_API_KEY=xxx .env文件:放在<LOCAL_USER>/.claude/skills/img-reader/.env,内容ZHIPU_API_KEY=xxx- 首次使用时提示用户注册并配置
安装依赖
python -m pip install zhipuai -q
特点
- 完全免费(glm-4v-flash 免费额度)
- 不是 MCP — Python 直接 HTTP 调用,不消耗 MCP 额度
- 中文 OCR 能力好
- 返回 JSON:
{"success": true, "result": "...", "provider": "glm-4v-flash"}
失败时自动降级到 Tier 2
失败情况:无 API Key、网络不通、API 报错
What ships with it
2 files 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.
- 10d ago First seen · 164 lines · 106 tokens per session scan A a9db28504b40
img-reader is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 1,580 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.