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/nullskymc/aurevoy/researchnpx skills add nullskymc/Aurevoy --skill researchgit clone --depth 1 https://github.com/nullskymc/AurevoyWhat 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 | $0.00062 | $0.01662 |
| Opus 5 | $0.00031 | $0.00831 |
| Sonnet 5 | $0.00012 | $0.00332 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
research 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 2d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
两种模式，先选一个再开干。
| 模式 | 何时 | 流程 |
|---|---|---|
| 快速报告（默认） | 主题单一、时效短、不需多对象结构化对比 | 检索 → 写报告 → 交付 |
| 深度报告 | 多对象/多切片、要可续跑、要字段对齐 | outline → 并行 deep JSON → 合成报告 → 交付 |
澄清：最多问 1 次（模式 / 时间范围 / 交付格式）。能默认则默认。
交付
| 形态 | 路径 | 何时 |
|---|---|---|
| 对话结论 | — | 用户只要几句话 |
| Markdown（默认文件） | research/<slug>/report.md 或 report/<slug>.md |
需归档、分享、可打开预览 |
| HTML | report/<slug>.html |
用户明确要 HTML / 单页 / 评分卡时间线等组件 |
规则：
- 未指定格式 → 文件用 Markdown。
- HTML 仅在用户要求或组件版式明显更合适时。
- 最终回复 = 路径 + 一句话摘要；不复述全文。
- 文件交付后
attach_content。HTML 须先bundle_report。 - 禁止把「按字段 key 全量展开」当作主报告。
- 改稿纪律：首次用
write落草稿；之后补证据/改段落用edit（精确 old→new），禁止为小改反复write整篇覆盖。
快速报告
web_search/web_fetch（必要时delegaterole=research）。不编造来源。- 直接写报告，结构：
# 标题
> as_of / 范围
## 结论
（5–10 行主线）
## 要点
- …
## 数据 / 对比
（表格）
## 风险与下一步
## 来源
- url
- HTML 时用下方组件骨架 +
bundle_report。 attach_content。
深度报告
1. 建骨架
目录：research/<topic_slug>/
outline.yaml
topic: …
topic_slug: …
as_of: "YYYY-MM-DD"
mode: deep
delivery: markdown # markdown | html | chat
items:
- id: a
name: 对象或切片 A
focus: 一句话
execution:
batch_size: 4
output_dir: results
fields.yaml（扁平；宁少勿滥）
fields:
- name: summary
category: 结论
description: 该项核心结论
required: true
- name: evidence
category: 证据
description: 关键事实与数据
- name: sources
category: 来源
description: URL 列表
required: true
事件/简报类：字段控制在 8 个以内；对比档案类可稍多。不要为无关切片硬套同一张 40 字段表。
2. 并行 deep
- 已有
results/<id>.json则跳过。 - 每批最多
batch_size个delegate（role=research），每 item 一个。 - 子任务：检索 → 按 fields 写 JSON → 不确定写
"[不确定] …"并列入uncertain→ 中文值 → 含item_id/item_name/sources。 - 校验（路径按实际 skill 位置填写）：
python <skill_dir>/scripts/validate_json.py -f fields.yaml -j results/<id>.json
- 每批结束汇报进度，默认继续下一批。
3. 合成主报告（必须）
读全部 JSON，写给人看的 report.md（或 HTML）：
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.
- 2d ago First seen · 195 lines · 62 tokens per session scan A 62a48ef40959
research is a skill published in the GitHub repository nullskymc/Aurevoy (10 stars, last pushed 26d ago), licensed MIT. It adds 62 tokens to every session and 1,662 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
create_profile_style_skill
【META SKILL】分析当前剪辑逻辑与风格，总结并生成一个新的可复用 Skill 文件，存入剪辑技能库。Analyze the current editing logic and style, summarize and generate a new reusable Skill file, and store it in the editing skill library.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
Paper Writing Workflow
Workflow phases for paper-writing tasks: triage, material inventory, research question, literature review, paper outline, data analysis summary, figure storyline, reader testing, and finalize packet. Each phase is a short contract — read the relevant rows for the current task only.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
deep-researcher
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.
llmtornado-tutorial-generator
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.