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 zhuanggenhua/BoardGame --skill safe-image-readinggit clone --depth 1 https://github.com/zhuanggenhua/BoardGameWrote 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/zhuanggenhua/boardgame/safe-image-reading)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/safe-image-reading"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/safe-image-reading/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/zhuanggenhua/boardgame/safe-image-reading"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/safe-image-reading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01803 |
| Opus 5 | $0.00023 | $0.00901 |
| Sonnet 5 | $0.00009 | $0.00361 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
safe-image-reading 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 11d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Image Reading
本 workflow 只服务当前用户需求中“必须从图片补足的判断”。读图过程本身不是交付;交付必须落到数据字段、规则合同、验收结论、排障事实或阻塞项。
触发
使用本 skill:
- 用户要求看图、读图、OCR、根据卡图/规则页/房间图录入、图片验收或截图审计。
- 任务涉及 JPG、PNG、WebP、atlas、SpriteSheet、卡牌裁图、规则页截图、UI 截图。
- 当前对话因原图、base64、图片上下文过大而变慢或报错。
- 图片是数据录入、规则提取、实现验收、UI 对比、资源核对、排障定位或审计判断的真相来源之一。
核心原则
- 先交接需求,不先泛读图片:必须写清用户要什么、业务对象是什么、图片需要补哪个字段/判断、结果要写回哪里。
- 默认轻量读取:普通单图先生成压缩图、低分辨率预览或单对象裁图给主线程读取;不要反复把原图或 base64 带进长上下文。
- 按需求返回结果:数据录入返回字段和合同状态;验收返回是否达标和失败点;排障返回图片能证明/不能证明的链路事实。
- 子代理只在升级场景用:大图、批量图、atlas/整页图、SpriteSheet、长线程安全读图或用户明确要求时,才交给子代理 / OCR / 外部开图。
- 一次读图,多轮复用:已形成合同或验收证据后,后续实现和审计读文字合同与图片引用,不重复读原图。
- 失败不硬试:图片链路导致上下文溢出、请求报错、OCR 不可用或裁图不可读时,换文本真相源、本地裁图/OCR、已有合同,或只把对应字段标为阻塞。
- 已锁合同优先:审计对象已有 locked 合同和实现对照矩阵时,不把 safe-image-reading 当普通续跑入口;只有合同缺主真相源、缺完整单对象图、来源冲突,或用户明确要求复核图片时才重新读图。
状态口径
读图结果只按当前验收目标判定:
passed:当前目标需要的字段全部锁定,可进入下一步。failed:图片能正向证明不是当前目标对象,或明确不满足验收目标。blocked:图片无法提供足够信息,例如空白、打不开、严重模糊、文字区缺失、裁切缺失。partial:图片仍可能属于目标对象,但只锁定部分必需字段。disputed:图片与其它真相源冲突,不能单边裁决。not-applicable:图片与当前目标无关。
边界:纯色/空白/打不开是 blocked,不是 failed;明确是非目标对象是 failed,不是 partial;只有“可能是目标但字段不全”才用 partial。
主线程流程
1. 锁图片判断点
记录:
- 原图或裁图路径。
- 需求类型:数据录入、规则录入、实现验收、UI 对比、资源核对、排障定位。
- 业务对象和现实作用。
- 图片要补足的字段、判断或证据。
- 输出落点:evidence、合同表、真相表、验收结果,或当轮回复。
2. 生成轻量输入
- 普通单图优先生成压缩图或低清预览。
- 文字、像素边界、小图标优先 PNG / WebP lossless;照片、纹理和渐变可用 WebP lossy / JPG。
- atlas、整页图或 SpriteSheet 先裁到单对象完整图;局部放大图只能辅助,不替代完整单对象图。
- 批量图先做 contact sheet 或分批裁图;规则/数据录入优先让子代理直读完整单对象裁图,OCR 只作索引或兜底。
- 如果轻量图已经足够判断当前目标,直接结论,不再升级开放式识图。
3. 读取或委托
主线程自己读图或委托子代理时,都必须带验收标准,不能变成开放式视觉描述。
子代理输入必须包含:图片路径、对象名、用户需求、图片判断点、通过条件、失败/阻塞/partial 边界、结果用途和返回格式。输出只允许结构化字段、结论、失败点、路径/hash;禁止返回 base64、data URL、markdown 图片或大段二进制内容。
参数错误时,修正调用形态后只重试一次。连续失败后换真相源,不继续同路硬试。
4. 写回
按需求写回:
- 数据 / 规则录入:写入 evidence、录入合同或真相表,至少包含对象、图片路径、hash、原文/字段、原子子句、结构化字段、合同状态。
- 实现验收 / UI 对比 / 资源核对:写入验收 evidence 或当轮回复,至少包含用户预期、图片判断点、状态、失败点、证据路径。
- 排障定位:记录图片证明的链路事实和下一步,不生成无关过程文件。
只有当前需求、既有 E2E 证据链或项目 workflow 明确要求独立图片验收产物时,才生成:
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.
- 11d ago First seen · 119 lines · 46 tokens per session scan A 16c82b7b1aa4
safe-image-reading is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,803 once invoked, about $0.0002 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…