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 instructions/jovandyaz/knowtis-app/claude-mdgit clone --depth 1 https://github.com/jovandyaz/knowtis-appWrote 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/instructions/jovandyaz/knowtis-app/claude-md)<a href="https://agentmods.dev/instructions/jovandyaz/knowtis-app/claude-md"><img src="https://agentmods.dev/badge/instructions/jovandyaz/knowtis-app/claude-md.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 | $0.03749 | $0.03749 |
| Opus 5 | $0.01875 | $0.01875 |
| Sonnet 5 | $0.00750 | $0.00750 |
| Haiku 4.5 | $0.00375 | $0.00375 |
Grade A, and why
knowtis-app CLAUDE.md 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Knowtis is a real-time collaborative notes platform built as an Nx monorepo with React frontend and NestJS backend. Key technologies: React 19, NestJS 11, PostgreSQL 16, Drizzle ORM, Yjs (CRDT), Socket.io, TanStack Router/Query, Zustand, Tiptap editor.
Important Rules
- Always use
pnpminstead ofnpmoryarnfor package management - No backwards-compatibility hacks — no re-exports from barrel files, no legacy shims, no "old key" comments. If something is renamed or moved, update all consumers. Clean breaks over compat layers.
- Barrels and re-exports — a package's root
index.tsis its public API and the only barrel that belongs (Nxenforce-module-boundarieslimits consumers to what that file exports): import@knowtis/*and@jovandyaz/*symbols from the package alias, never by deep path. Inside an app or package, import from the file that defines the symbol; don't addindex.tsbarrels, and if a change would extend one, replace it instead — point its consumers at the source files and delete it (NestJS: barrels breed circular dependencies between modules and providers; Vite: they defeat tree-shaking and slow the dev server). Never re-export a symbol that another package or folder owns. - Always consult official docs — before implementing or configuring anything involving external tools, libraries, or services (Vercel, Railway, Nx, etc.), AND before debugging library-specific issues (auth flows, init APIs, error codes), fetch the latest official documentation using Context7 MCP, web search, or CLI help. Never assume behavior from memory alone.
- Minimal comments — default to no inline comments. Only write JSDoc on exported APIs,
TODO/FIXMEmarkers, or comments that explain a non-obvious WHY (hidden constraint, subtle invariant, framework quirk workaround). Never paraphrase code, never reference the current task/PR/fix in comments.
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 · +7 lines · +623 tokens per session 640872fb0f66
- 4d ago First seen · 212 lines · 3,126 tokens per session scan A 427ef13f9d92
knowtis-app CLAUDE.md is an instructions file published in the GitHub repository jovandyaz/knowtis-app (3 stars, last pushed today), licensed MIT. It adds 3,749 tokens to every session, about $0.0187 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 instructions, from other repositories
plan42 AGENTS.md
AGENTS.md instructions for sh1nj1/plan42, covering agent development guide, documentation language, documentation index and agent operating rules.
escurel CLAUDE.md
Claude Code instructions for DataZooDE/escurel, covering how we work on escurel, nine principles, what this looks like in practice, locked decisions (current bootstrap) and keeping the consumer skill in sync.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
DocMason copilot-instructions.md
Copilot instructions for JetXu-LLM/DocMason, covering docmason github copilot notes and copilot-specific delta.
Kiln AGENTS.md
AGENTS.md instructions for Kiln-AI/Kiln, covering project overview, project goals, tech stack, agent tools and agent prompts.
student-llm-wiki AGENTS.md
Instructions for IssacW228/student-llm-wiki, covering student llm wiki — agent instructions, 操作规则 operation rules, token预算规则(最高优先级), 架构 architecture and 命令 commands.