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 koersliven/Lore --skill lore-initgit clone --depth 1 https://github.com/koersliven/LoreWrote 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/koersliven/lore/lore-init)<a href="https://agentmods.dev/skills/koersliven/lore/lore-init"><img src="https://agentmods.dev/badge/skills/koersliven/lore/lore-init/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/koersliven/lore/lore-init"><img src="https://agentmods.dev/badge/skills/koersliven/lore/lore-init.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 | $0.00014 | $0.01280 |
| Opus 5.5 | $0.00006 | $0.00512 |
| Sonnet 5.5 | $0.00003 | $0.00256 |
| Haiku 4.5 | $0.00001 | $0.00128 |
Grade A, and why
lore-init 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/init-context — Project Context Initialization
When to Trigger
- User explicitly invokes this skill
- Agent enters a project with no
.ai-context/snapshot.md - Agent detects a project it has never seen before (no snapshot, no CLAUDE.md architecture section)
Purpose
Complete the 0→1 knowledge capture. Extract the developer's mental model of the project into structured .ai-context/ files so the agent reaches a minimum viable understanding level.
Process
Step 1: Project Discovery
First, scan the project to understand basics:
- What language/framework? (package.json, pom.xml, go.mod, etc.)
- What are the entry points? (controllers, routes, main functions)
- Module structure (directories, packages, workspaces)
- External dependencies (imports, package.json dependencies, Maven GAVs)
Report what you found, then proceed to questioning.
Step 2: Guided Questioning
Ask the user these questions in batches (3-5 at a time, conversational tone). Adapt questions based on what you already discovered.
Category A: External Dependencies
- "这个项目调用了哪些外部服务或 API?对方提供什么能力?"
- "有哪些依赖定义在外部 JAR 包里,你看不到源码的?"
Category B: Configuration
- "配置存在哪里?(Diamond / env / 数据库 / 本地文件?)"
- "有哪些关键配置项会影响行为?改了什么配置会导致线上出问题?"
Category C: Data Layer
- "数据存储在哪里?有分库分表吗?规则是什么?"
- "缓存策略是什么?什么数据被缓存?"
Category D: Business Context
- "这个项目的业务场景是什么?服务于谁?"
- "核心业务流程是什么?能描述 3-5 个关键步骤吗?"
Category E: Implicit Contracts
- "有哪些未文档化的约定?"
- "有哪些代码不能碰?为什么?"
- "踩过哪些坑?哪些设计是因为历史事故才这样的?"
Step 3: Generate Initial Files
Based on answers, create:
.ai-context/snapshot.md:
- Project overview (what it is, who it serves)
- Core flows (end-to-end process descriptions)
- Key decisions (WHY-level, with source tracing)
- Constraints (things that must not change)
- External dependencies (things AI cannot read from source)
- Config index (where to find configurations)
- Business context (scenarios, relationships)
- Glossary (terminology)
Each entry must include:
- 来源: {{user name}}, {{date}}, /init-context guided session
- 置信度: high (directly from project owner/developer)
- 验证状态: verified
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.
- 1mo ago First seen · 153 lines · 14 tokens per session scan A e4a116c10e35
lore-init is a skill published in the GitHub repository koersliven/Lore (5 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,280 once invoked, about $0.0001 per session on Opus 5.5. 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
context-end
Close a workspace session by reviewing a proposed summary, recording approved outcomes, updating state and decisions, and checking repository safety. Use only when the user explicitly asks to end, close, or hand off the current session.
context-update
Save a brief mid-session checkpoint to this workspace and update current state only when a priority or open thread changed. Use only when the user explicitly asks to checkpoint or save current progress.
faf-expert
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.
contextos-workspace
Run Context OS continuity and lifecycle workflows in a user-selected Context OS workspace. Use when asked to inspect, set up, update, or close a Context OS session.
personal-context
Interview the user to build or update a reusable "about me" context file for AI tools — who they are, their role and background, how they work, and how they want AI to help. Use when the user says "build my personal context", "create my about-me context", "set up my AI context", "update my personal context", or wants…
refresh-context
Review and refresh an existing personal-context.md or company-context.md — check what has gone stale, fill gaps against the current template, and update the file. Use when the user says "refresh my context", "review my context", "is my context still up to date", "my context is stale", or after a change in role, offer…