Borrowing it
Nothing to install: this file belongs to VOD-Studio/violet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/VOD-Studio/violet/release/2.0/.agents/skills/session-notes/SKILL.mdgit clone --depth 1 https://github.com/VOD-Studio/violetWrote 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/vod-studio/violet/session-notes)<a href="https://agentmods.dev/skills/vod-studio/violet/session-notes"><img src="https://agentmods.dev/badge/skills/vod-studio/violet/session-notes/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/vod-studio/violet/session-notes"><img src="https://agentmods.dev/badge/skills/vod-studio/violet/session-notes.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 | $0.00063 | $0.03361 |
| Opus 5 | $0.00032 | $0.01681 |
| Sonnet 5 | $0.00013 | $0.00672 |
| Haiku 4.5 | $0.00006 | $0.00336 |
Grade A, and why
session-notes 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 today.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Notes
自动捕获在任务完成并验证后执行;显式 /session-notes 可补录既有成果,也可按用户要求重写已有文章。只通过博客 MCP 入库,不直接调用 HTTP 或数据库。用户只要求维护本 skill 时,不触发内容入库。
渐进加载
- 从当前会话的最终成果筛候选:
类型 + 暂定主题 + 一句价值判断 + tags,保留相关证据出处;不要把整场会话压成摘要后直接入库。 - 笔记默认只读本文件;分诊、拆条或脱敏边界不清时读 references/decision-guide.md 对应小节。文章的新建、重写、恢复入库都必须先读 references/article-workflow.md,完成写作简报、取证、结构选择和成稿审查。
- 先淘汰琐碎、重复和不满足意图测试的候选。文章必须给具体读者带来明确收益,并选择适合材料的组织方式;不能仅因改动多、功能完整或有参考长文就升为文章。
- 正常入库只提问一次;MCP 不可用时允许追加一次“保存项目待恢复稿 / 不保存”提问。提问和成功报告均不回显正文。
1. 重量分诊
- 功能级:已有完整成果和行为证据,能解释非显然机制、设计取舍、故障因果、实验发现或可复用操作。生成
0..1篇可独立阅读的工程文章;实际保存为草稿还是发布,由第 5 节的用户授权与第 6 节的 MCP 权限共同决定。 - 经验级:形成明确的坑、根因、修法或教训。按知识点生成
0..N条笔记。 - 琐碎或重复:不生成内容,不提问,保持沉默。价值不明确时按此处理。
完整落地不自动等于文章级。材料只支撑单点经验时,自动捕获降为笔记或不写;用户显式要求文章时不得偷换成摘要,应说明缺失的关键材料。draft 是当前存储状态,不降低成稿标准,也不代表永久禁止发布。
2. 拆条与查重
- 一条笔记只记录一个可独立检索的主题;同一因果链的现象、根因、修法保持一条。
- 笔记必须通过意图测试:首要目的是记录知识、供未来检索。情绪、状态、进度、碎碎念全部丢弃。
violet-notes可用时,成文前调用list_notes查重;仅对疑似同主题项调用get_note。- 已有同主题笔记且本次有新增事实时形成更新稿,后续调用
update_note;没有新增价值时丢弃;不得新建近义重复项。MCP 不可用时无法查重,恢复稿必须记录dedupe_status: pending,恢复入库前再查重并决定 create、update 或丢弃。 - 用户要求重写已有文章时,先用
get_post读取当前正文和元数据,以该 ID 更新;没有 ID 才用search_posts定位同主题草稿。禁止把改稿当新文章创建,也不自动覆盖已发布文章。
3. 成文
- 中文书写,术语与代码保持英文;事实陈述必须有对应证据,推演在结论旁说明前提和未复现范围。
- 笔记:默认“现象 → 根因 → 修法”,教训类可省略根因;
150..400中文字,复杂根因最多800字。标题可选,有则直接点明可检索的知识点。 - 文章:按文章专用流程先形成内部写作简报,识别材料类型并选择结构;成稿须通过读者收益、结构适配、证据边界、材料取舍与中文表达门禁。任一项失败先改稿,不进入裁定或入库。
- 文章标题准确说明对象和读者收益。篇幅、章节、图表与代码块均由材料决定,不设配额;不能用长篇、固定目录或视觉形式替代内容判断。
- 每项给
2..4个英文小写 tags,如redis、css、deploy。代码块标语言;完整示例必须执行最终版本再附真实输出,源码摘录不得冒充独立可运行程序。 - 不写营销腔、工具操作流水账或虚构第一人称经历。文章在结构审查后执行专用流程内的表达检查,不依赖其他写作 skill;润色不能代替结构重写,也不能改变事实和技术含义。
4. 双层敏感门禁
对每篇成文分别写入临时文件并运行:
python3 .agents/skills/session-notes/scripts/scan-sensitive.py <file>
- 输出
clean且退出码0才算机械扫描通过;退出码1为命中,其他退出码按失败处理。 - 脚本结论优先于模型判断;不得使用白名单、跳过标记或自我豁免。
- 模型继续检查脚本覆盖不到的语义敏感信息:可识别的服务器昵称、真实业务数据、内部路径、账号、内部拓扑和组合后可定位系统的信息。
- 能脱敏则改写并重新扫描,例如真实主机名改为“生产服务器”、绝对用户路径改为“本地项目目录”。
- 脱敏后失去价值时,保留必要内容,在开头标注
> 含待人工处理的敏感信息,并降级为“仅草稿”。 - 每篇成文进入裁定前都必须完成脚本扫描和模型语义自查。
clean仅代表敏感扫描通过,不代表文章质量合格。
What ships with it
3 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.
- today Changed · +3 lines · +13 tokens per session 1b8bbd33ec5c
- yesterday Changed · +37 lines 2ee9025e7773
- 4d ago First seen · 91 lines · 50 tokens per session scan A 6e6d92be42e6
session-notes is a skill published in the GitHub repository VOD-Studio/violet (3 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 3,361 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 2026-09-05.
Other skills, from other repositories
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
memory-safety-c-cpp
Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…
extension-upload
Package a script tool under /.config/agenvoy/tools/script/ into a tar.gz and publish to pkg.agenvoy.com registry. Keyword picker, dep/key detection, config-stored email (ask + lowercase + persist), ask version, email verification gate, multipart upload with downgrade/unique guards.
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.
summary-style-guide
Tone and length conventions for email summaries — voice, verb tense, what to include vs omit, and target sentence count. Read this when writing the prose Summary line for each email so the voice is consistent across the report.