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 ssmurfgg04-gif/context-m --skill auto-target-trackergit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/auto-target-tracker)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/auto-target-tracker"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/auto-target-tracker/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/ssmurfgg04-gif/context-m/auto-target-tracker"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/auto-target-tracker.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 | $0.00081 | $0.02383 |
| Opus 5 | $0.00041 | $0.01192 |
| Sonnet 5 | $0.00016 | $0.00477 |
| Haiku 4.5 | $0.00008 | $0.00238 |
Grade A, and why
auto-target-tracker 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自动目标进度追踪器
触发条件
当对话中出现以下条件时自动触发:
- 用户发送了图片(特别是学习笔记、进度截图、健身记录、任务清单、创作作品等)。
- 用户在设定的目标时间段(如 08:30, 10:00, 20:00)发送了图片。
- 用户明确说"帮我记一下"、"看下进度"、"打卡"、"更新一下"等。
工作流程
1. 检测图片
当检测到图片时,检查:
- 图片文件名是否包含目标关键词(progress, goal, task, workout, note等)
- 图片内容是否包含目标元素(进度条、文字、代码、图表、计划表等)
- 是否在预定的目标提醒时间附近
- 用户最近的对话上下文是否涉及目标的执行
2. 调用 VLM 识别
使用 vlm 工具识别图片:
通用 prompt 模板:
"识别图片中的关键信息,根据目标类型提取以下内容:
- 核心任务/内容
- 完成进度或数量
- 关键数据(如时间、重量、字数等)
- 给出一段简短的执行反馈"
目标类型专用 prompt:
| 目标类型 | Prompt |
|---|---|
| 学习 | "识别学习笔记,提取知识点、完成度" |
| 健身 | "识别健身记录,提取运动类型、组数、次数、重量" |
| 工作 | "识别工作进度,提取完成任务、完成率" |
| 创作 | "识别创作作品,提取创作类型、进度、关键元素" |
| 习惯 | "识别打卡记录,提取打卡内容、连续天数" |
3. 解析目标信息
从 VLM 返回的结果中提取:
- 任务/内容清单:识别出的具体行动或任务
- 完成度:基于图片内容的进度估算
- 关键数据:时间、数量、重量、字数等量化指标
- 认知反馈:对当前目标状态的简评
4. 记录到目标日记
调用edit_daily工具将识别结果记录到当天的日常笔记中
5. 反馈给用户
向用户确认识别结果:
已记录你的目标打卡:
📝 识别结果:
核心内容:你拍的是今天的英语单词表,一共记了 15 个新词。
进度估算:今天的单词任务全部搞定,进度打败了 80% 的学习党。
建议:有两个单词的拼写有点模糊,明天复习的时候记得多看两眼。
记录准确吗?要帮你存进今天的目标日记里吗?
记录格式
目标日记条目示例
## 20:00 打卡记录
**目标类型**: 📚 学习
**图片**: 
**VLM识别结果**:
| 任务/内容 | 进度/数量 | 状态 |
|----------|----------|------|
| 英语单词 (Unit 1) | 15 个 | 已完成 |
| 数学练习 (第3章) | 80% | 进行中 |
| **总计** | | **今日达成 2/3** |
**关键数据**:
- 学习时长: 2小时
- 专注度: 高
**备注**: 自动识别,用户确认正确
---
## 10:30 健身打卡
**目标类型**: 🏃 健身
**图片**: 
**VLM识别结果**:
| 运动类型 | 组数 | 次数 | 重量 | 状态 |
|---------|------|------|------|------|
| 卧推 | 4 | 12 | 60kg | ✅ 完成 |
| 深蹲 | 4 | 10 | 80kg | ✅ 完成 |
| 引体向上 | 3 | 8 | 自重 | ⚠️ 少一组 |
| **总计** | | | **今日达标** |
**关键数据**:
- 总重量: 2640kg
- 训练时长: 45分钟
**备注**: 引体向上少完成一组,下次补上
与目标系统的集成
每日汇总
在每天晚上 22:00 的汇总中,包含:
- 今日所有打卡记录
- 目标达成率分析
- 与目标的对比(如果设置了目标)
周/月报告
在周报告中,包含:
- 本周有效执行时长
- 目标覆盖范围
- 连续打卡天数
- 动态难度调整建议:如果连续达标,则建议提升下周任务量
常见使用场景
场景1:学习打卡
用户行为:发送手写笔记照片
自动识别:
- 提取知识点
- 计算学习进度
- 记录到学习日志
反馈示例:
📚 识别到学习笔记:
- 机器学习监督学习算法(已完成)
- 梯度下降优化器(进行中)
- 正则化防过拟合(未开始)
进度:33% | 预计还需 2 小时完成
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.
- 10d ago First seen · 318 lines · 81 tokens per session scan A f111d051e825
auto-target-tracker is a skill published in the GitHub repository ssmurfgg04-gif/context-m (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 2,383 once invoked, about $0.0004 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
digest
NOTE: this skill requires connected chat / email / project-tracker / docs MCPs, which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Cross-tool rollup of what's pending, what shipped, and what's blocked across chat / email / project tracker /…
recap
Read-only orientation — render a scannable table of what just happened so you can situate yourself. Modes: '/recap' (this session), '/recap arc' (the last product arc), '/recap commit' (the last commit), '/recap push' (the last push's commits — what I sent up), '/recap pull' (the last pull's changes — what came down…
statusline
Install or remove the aria-knowledge status-line meter — a context-window progress bar plus the rolling 5-hour and 7-day plan-usage percentages, shown at the bottom of the Claude Code CLI. Use when the user says '/statusline', 'add a context meter', 'show context usage in the status line', 'show my 5-hour usage'…
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
calendar
Manage calendar events via CalDAV (Google/iCloud/Nextcloud) or local ICS files. View, create, and query events.