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/yipng05-max/-skills/grounded-codingnpx skills add yipng05-max/-skills --skill grounded-codinggit clone --depth 1 https://github.com/yipng05-max/-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/yipng05-max/-skills/grounded-coding)<a href="https://agentmods.dev/skills/yipng05-max/-skills/grounded-coding"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/grounded-coding.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 | $0.00230 | $0.07013 |
| Opus 5 | $0.00115 | $0.03506 |
| Sonnet 5 | $0.00046 | $0.01403 |
| Haiku 4.5 | $0.00023 | $0.00701 |
Grade A, and why
grounded-coding 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 4d 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
程序化扎根理论编码
对访谈记录或其他质性资料进行系统化的扎根理论编码分析。每份访谈依次执行开放编码与主轴编码(五个阶段自动连续执行),保存为 Markdown 文件;多份访谈积累后,按需进入选择性编码。
启动:获取基本信息
当用户触发此skill时,首先获取以下信息(如用户未提供,则主动询问):
- 质性资料路径:用户上传或提供的访谈记录/质性资料的本地文件路径(支持PDF、Word、TXT等格式)
- 研究领域:用户所在的研究领域(如教育学、管理学、社会学等)
- 研究主题:用户正在研究的具体主题
- 被访者信息:被访谈者的身份描述(如"某小学教师"、"创业者A"等)
- 研究议题焦点(可选):用户特别关注的研究议题或分析重点
- 访谈序号与既有编码表(持续比较关键信息):
- 这是你研究中的第几份访谈?(第一份 / 第N份)
- 如果是第二份及以后:之前访谈的累积编码表是否可以提供?
请提供文件路径,或直接粘贴类属列表,格式如下:
类属1:[类属名称] 包含编码:编码A, 编码B, ... 属性1:[名称](维度:[极端A] ←→ [极端B]) 属性2:[名称](维度:[极端C] ←→ [极端D]) 类属2:... - 如果是第一份访谈,直接开始全新建构。
如果用户在触发时已经提供了部分信息(如直接给出文件路径和研究主题),不要重复询问已知信息,只补充缺失的必要信息。
收到基本信息、读取质性资料全文后,在进入编码之前,询问研究者是否希望提供示范编码:
"在正式编码前,你可以选择: A. 研究者示范:你先对文本中任意一小段(3–5 个句群)做示范编码,AI 会识别你的编码风格,然后按你的风格完成后续开放编码 B. AI 直接编码:跳过示范,AI 按照标准原则直接开始
哪种方式?(选 B 或不回应则直接开始)"
若研究者选择 A(研究者示范):
- 请研究者提供示范片段及其对应编码(格式:
S1 "原文" → 编码标签) - AI 分析示范编码的风格特征,明确说明:
- 动名词使用程度:高度动名词化,还是更多名词短语?
- 抽象层次:贴近原文(描述性),还是已有一定理论提炼?
- 粒度:每个句群一个编码,还是允许多个?
- 用词风格:倾向本土化表达,还是理论术语?
- 输出风格确认:
"我理解你的编码风格是:[描述]。我将按照此风格完成后续开放编码。如有偏差,请随时纠正。"
- 按研究者风格继续执行五阶段流程
若研究者选择 B 或未回应:
直接进入五阶段,按标准原则编码。
执行流程(五阶段连续执行)
第一阶段:整体主题概览
阅读完全部质性资料后,提炼出几个大的主题方向,为后续微分析提供全局视野。
输出格式:
- 列出3-6个大的主题,每个主题附简要说明(1-2句话)
- 说明各主题在资料中的大致分布和权重
这一步的目的是让研究者在进入逐句编码之前,先对资料有一个整体认知框架。就像阅读一本书之前先浏览目录,整体主题概览帮助研究者明确后续微分析的方向和重点。
第二阶段:开放编码
开放编码是扎根理论的基础阶段,目标是从原始资料中逐步建构概念。包含三个连续步骤,对应从具体到抽象的逐步提升:
- 识别事件:逐项识别资料中的事项、事情、事务,进行命名(抽象层次较低)
- 提炼类属:对具体事件进行分类合并,形成概念(抽象层次较高)
- 分析类属:定义类属内容,分析特征,进行属性与维度分类
步骤一:识别事件(逐句微分析)
针对质性资料进行逐句微分析,逐项识别出资料中的事项、事情、事务,进行命名。这一步的抽象层次较低,紧贴原始资料——回答的是"这里发生了什么"。
编码原则:
- 逐句编码——按句群进行,不遗漏任何语句。只有纯粹的单词应答(独立成句,如仅有"嗯"、"对"、"好的")可以跳过,且必须在编码结果中标注"已跳过"。其余所有语句,无论看起来信息量多少,都必须给出编码。某句话是否重要,是研究者的判断权,不是 AI 的判断权;当不确定时,给出描述性编码(如"重复前述观点""表达不确定"),而不是跳过
- 优先使用动名词形式——GT 开放编码的标准格式是动名词(如"强调自主性""回避直接冲突""将平台规则合理化"),而非名词短语(如"自主性""冲突回避""规则合理化")。动名词保留了行动感和过程性,符合 GT 追问"正在发生什么"的分析取向。编码应简洁,通常 4–8 字,不宜过长
- 每个句群给出一个最合适的编码——同一个编码可以在不同句群重复出现(这说明该现象反复被提及)
- 紧扣研究议题——编码时重点关注与用户研究主题和研究议题相关的内容
- 禁止对仗整齐——编码标签的字数和句法结构应由数据内容决定,而非由输出形式决定。如果检查发现大多数编码字数相近、结构相同(如全部是四字动名词短语),说明在优化形式而非忠实于数据,必须主动打破这种整齐感。有些编码天然更长,有些更短,有些是受访者原话的动名词化,有些是描述性的过程短句,形态多样才符合 GT 的细粒度要求
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.
- 4d ago First seen · 517 lines · 230 tokens per session scan A 64909031194b
grounded-coding is a skill published in the GitHub repository yipng05-max/-skills (283 stars, last pushed 4mo ago), licensed MIT. It adds 230 tokens to every session and 7,013 once invoked, about $0.0011 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.