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/mm-weber/loremaester/chroniknpx skills add mm-weber/loremaester --skill chronikgit clone --depth 1 https://github.com/mm-weber/loremaesterWrote 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/mm-weber/loremaester/chronik)<a href="https://agentmods.dev/skills/mm-weber/loremaester/chronik"><img src="https://agentmods.dev/badge/skills/mm-weber/loremaester/chronik.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 | $0.00085 | $0.01280 |
| Opus 5 | $0.00043 | $0.00640 |
| Sonnet 5 | $0.00017 | $0.00256 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
chronik 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Campaign Chronicle Update Assistant
Update the Campaign Chronicle from PlayerNotes with strict information-exchange precision. The Chronicle is the campaign's canonical record of what happened — if information gets lost in summarization, it's lost forever.
The Cardinal Rule
For every NPC interaction in the Chronicle, a reader must be able to answer: "What exactly does each party know after this conversation that they didn't know before?"
If the Chronicle entry doesn't answer that question, it's incomplete.
Source of Truth Hierarchy
Per the vault's CLAUDE.md:
- PlayerNotes = what HAPPENED (player actions, canon)
- In-game calendar / dates = when events occurred (canon)
- Session prep files = what was PLANNED (context, may or may not be canon depending on player actions)
The Chronicle synthesizes all three, but PlayerNotes always win on what occurred.
Workflow
Phase 1: Read and Identify
- Read the PlayerNotes for the target session(s)
- Read all linked Session prep files — find the session folder under
Sessions/Session N/and read every sub-file. These contain GM context about NPC motivations, hidden agendas, and what information NPCs were trying to extract. - Read referenced NPC files — for every NPC mentioned in the player notes, read their note in
NPC/. Pay attention to faction, relationships, and any campaign-connection sections. - Check in-game dates — if the vault tracks dates (e.g. via a calendar plugin or in-frontmatter
game_date:), anchor each event chronologically.
Phase 2: Extract Information Exchange Events
For EVERY scene where a PC talks to an NPC, build this matrix:
Scene: [PC] meets [NPC] at [Location]
├── What PC SHARED (explicitly stated in PlayerNotes)
│ └── List each piece of information with the exact phrasing from the notes
├── What PC WITHHELD or REFUSED to share
│ └── Note what was asked for and refused, with the reason if given
├── What NPC GAINED (cross-ref with Session prep — did the NPC learn something they were specifically after?)
│ └── Connect shared info to NPC's hidden goals from prep files
├── What PC LEARNED (new facts, NPC backstory, world info)
│ └── Include NPC revelations, offers, philosophy shared
└── What was OFFERED but not yet resolved
└── Deals, trades, future commitments
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 · 97 lines · 85 tokens per session scan A 8292e8e5c826
chronik is a skill published in the GitHub repository mm-weber/loremaester (19 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,280 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 2026-08-30.
Other skills, from other repositories
figure-remap
Extract single figures from PDF textbooks on-demand with built-in QC verification. Primary use: when writing/supplementing a note that needs an embedded figure (anatomy, classification, algorithm, imaging). Each call checks an existing fast-path crop, re-extracts from PDF if missing/wrong, retries with local-vision…
textbook-to-md
Convert PDF/EPUB textbooks to searchable markdown files for an AI agent's own reference. Use this skill whenever: (1) the user asks to convert a textbook/PDF chapter to markdown, (2) you need to search textbook content and no markdown version exists yet, (3) batch-converting a set of reference books into a knowledge…
lecture-to-notes
Turn a lecture/conference recording (video or audio: MOV/MP4/M4A/MP3/WAV) into structured vault notes via local GPU transcription + slide extraction — 演講影片, 演講音檔, 上課錄影, '整理演講', '影片轉筆記', '音檔轉筆記', or a dropped media file. Handles batch runs.
dmcheck
Deterministic conduct verdicts for live tabletop sessions — CI for running a game. Use it when you want to know how a session went as a table: "did I leave anyone hanging?", "was that roll ever acknowledged?", "did the fight end without anyone being told?", "why did the table go quiet for five minutes?", post-session…
invest_analysis
Systematic investment research workflow for A-share and Hong Kong stock markets using AI-powered analysis. Use when conducting sector selection, supply chain analysis, financial report verification, or market sentiment evaluation. 系统化的 A 股/港股投资研究工作流程,适用于赛道筛选、产业链分析、财报验证和市场情绪评估。.
beautiful-article
把用户提供的素材(网页 URL / PDF / DOCX / Markdown / 纯文本 / 截图 / 粘贴材料)编辑、设计成一篇美丽的、可离线打开和分享的单文件 HTML 网页文章。基于 reacticle 组件协议:不手写裸 HTML/CSS,而用语义组件 + 受主题约束的 Raw 自由层;按 source→规划→双确认→生成→终审→修复的小型 harness 流程推进,默认 100% 信息保留的长文。触发场景:把 URL/PDF/DOCX/文章做成网页文章 / 长文 / briefing / 解释文 / 视觉文章 / 教程 / 审阅复盘 / 方案分析,'render this as a beautiful web…