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/jedeiah/codex-read-image/read-imagenpx skills add Jedeiah/codex-read-image --skill read-imagegit clone --depth 1 https://github.com/Jedeiah/codex-read-imageWrote 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/jedeiah/codex-read-image/read-image)<a href="https://agentmods.dev/skills/jedeiah/codex-read-image/read-image"><img src="https://agentmods.dev/badge/skills/jedeiah/codex-read-image/read-image.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 | $0.00065 | $0.01155 |
| Opus 5 | $0.00032 | $0.00577 |
| Sonnet 5 | $0.00013 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
read-image 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 3d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read Image(图片读取)
何时使用
- 用户提供了图片路径或拖入图片,要求"看一下 / 读取 / 描述 / 分析 / 识别";
- 需要把图片内容变成文字:截图里的报错、图表数据、设计稿、证件扫描件、照片等;
- 用户提问时附带了图片文件。
工作流程
-
确认图片存在:检查用户给的路径是否真实存在,支持 png / jpg / jpeg / webp / gif。
-
运行脚本(脚本会先 base64 编码图片,再调用视觉模型)。脚本位于插件目录的
scripts/下,相对于本 SKILL.md(skills/read-image/)是../../scripts/read_image.py:python3 <插件目录>/scripts/read_image.py <图片路径> [更多图片...] --prompt "<用户的具体问题>"查找脚本位置后运行,例如安装目录为
~/.codex/.tmp/marketplaces/codex-read-image/plugins/read-image时:python3 ~/.codex/.tmp/marketplaces/codex-read-image/plugins/read-image/scripts/read_image.py /tmp/screenshot.png \ --prompt "详细描述这张截图的内容,包括其中的报错信息" -
读取脚本输出:脚本把视觉模型的识别结果打印在终端,作为后续回答的事实依据。
-
回复用户:把识别结果转述给用户(中文),如果用户在原问题上继续追问,基于识别文本继续处理(总结、翻译、找 bug、提取数据等)。
配置检查(首次使用必须)
推荐方式:插件目录里的 .env(卸载插件时随插件一起删除)。首次使用如果只有
.env.example 模板,先复制一份:cp 插件目录/.env.example 插件目录/.env,再编辑填写。
也可以复制一份到 ~/.config/read-image/.env 作为备用(插件升级时不会被覆盖)。
两者结构相同,填好即可,不需要动 shell 配置:
| 环境变量 | 必填 | 说明 |
|---|---|---|
READ_IMAGE_API_KEY |
是 | 视觉模型服务的 API 密钥 |
READ_IMAGE_BASE_URL |
否 | OpenAI 兼容接口地址,默认 https://api.openai.com/v1 |
READ_IMAGE_MODEL |
否 | 视觉模型名,默认 gpt-4o-mini |
READ_IMAGE_THINKING |
否 | 思考模式 auto/on/off,默认 auto(glm 系列自动开启,其他模型关闭) |
常见可用的视觉模型示例:gpt-4o-mini / gpt-4o(OpenAI)、qwen-vl-max(通义千问,DashScope 兼容模式)、glm-4.6v-flash / glm-4v-flash(智谱,免费)、SiliconFlow 上各家开源视觉模型。
.env 示例(编辑插件目录里的 .env 填值):
READ_IMAGE_API_KEY=你的密钥
READ_IMAGE_MODEL=glm-4.6v-flash
READ_IMAGE_BASE_URL=https://open.bigmodel.cn/api/paas/v4
READ_IMAGE_THINKING=auto
上面是智谱免费模型示例(GLM-4.6V-Flash);不填时脚本默认使用 gpt-4o-mini + https://api.openai.com/v1。如果都没有 READ_IMAGE_API_KEY,脚本会明确报错。此时应告诉用户按上面示例补上,改完重启 Codex 再试。配置优先级:命令行参数 > 环境变量 > 插件目录 .env > ~/.config/read-image/.env > 内置默认值。.env 不在 Git 仓库里,插件升级不会覆盖它。
当前 DeepSeek 接口不支持图片输入,需要另配一个支持视觉的模型服务,在
.env里填写即可。
注意事项
- 大图片可能超过视觉模型限制:可先用 macOS 自带命令缩小(
sips -Z 1024 原图 --out 缩小图.png)再识别。 - 一次可以传多张图,脚本会逐张识别并分别输出。
- 图片只会上传到配置的视觉模型服务;不要把 API 密钥写进 prompt 或输出。
.env里存有你的密钥,不要把这个文件或整个插件目录分享给别人。- 识别结果来自第三方视觉模型,可能与原图存在细节差异,回答时注意这一点。
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.
- 3d ago First seen · 69 lines · 65 tokens per session scan A c5b45a3c04a0
read-image is a skill published in the GitHub repository Jedeiah/codex-read-image (3 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,155 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 2026-08-31.
Other skills, from other repositories
stop-that-shit
Keep coding agents focused on requested and necessary work. Use for bounded changes, review-only tasks, scope creep, speculative hardening, unnecessary hashing or dependencies, repeated audit loops, or when the user invokes Stop That Shit.
codex-auth-setup
Install or refresh codex-multi-auth for the official Codex CLI, run first login, and verify account health and routing.
example
Example fixture skill for scanner regression coverage.
codexu-pr-review
Review codexU pull requests and decide whether they should be merged, changed, split, declined, or kept as a fork based on product positioning, roadmap, privacy, data semantics, native macOS design, architecture, scope, and verification. Use for PR review, mergeability assessment, contribution triage, and feature-fit…
dev-flow
Use Dev Flow for bounded Codex software development tasks: implementation, bug fixes, refactoring, targeted testing, development delivery, and explicit parallel batches isolated in separate Git worktrees. It may be selected implicitly for those tasks or explicitly with $dev-flow-codex:dev-flow. Do not create a Dev…
codexkit-repository-maintenance
Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.