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/ryannli/opennote/claude-mdgit clone --depth 1 https://github.com/ryannli/opennoteWrote 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/ryannli/opennote/claude-md)<a href="https://agentmods.dev/instructions/ryannli/opennote/claude-md"><img src="https://agentmods.dev/badge/instructions/ryannli/opennote/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 5.1 | $0.01499 | $0.01499 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
opennote 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 5d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenNote — AI-Powered Personal Info Bank
Config
- Timezone: TIMEZONE_PLACEHOLDER
What This Repo Is
This is a Personal Info Bank — a simple, chronological repository for capturing anything: thoughts, notes, images, links, meetings, and more. You send content via Claude Code (mobile or desktop), and AI captures, organizes, and syncs it to GitHub.
Workflow
The user sends content via Claude Code. Claude's job is to:
- Capture the content into the correct file and directory
- Commit with a clear message
- Push to GitHub so everything stays synced
Directory Structure
opennote/
├── CLAUDE.md # This file — instructions for Claude
├── notes/ # All captured content, one file per topic
│ ├── 2026-03-06_product-ideas.md
│ ├── 2026-03-07_meeting-with-alex.md
│ ├── 2026-03-08_book-highlights.md
│ └── ...
└── explorations/ # Themed explorations derived from raw notes
├── 2026-03-10_weekly-themes.md
├── 2026-03-15_project-brainstorm.md
└── ...
How to Record a Note
When the user sends a piece of text, thought, information, or idea:
- Determine the current date (YYYY-MM-DD format)
- Determine a short, descriptive topic slug (e.g.,
product-ideas,meeting-with-alex,book-highlights) - Create a new note file:
notes/YYYY-MM-DD_topic-slug.md - Use this format:
---
date: YYYY-MM-DD
created: "HH:MM"
summary: 1-2 sentence summary of the note's core content, enabling quick scanning and progressive exploration.
---
# Title
<content goes here>
Format rules:
- YAML frontmatter at the top with:
date: the date of the notecreated: the time it was created (use the timezone specified in Config above). Get the current time withTZ='<timezone>' date '+%H:%M'.summary: 1-2 sentence summary of the note's core content — this enables progressive exploration (scan summaries first, then load full content only when needed)
- One topic per file — if the user sends multiple unrelated items, create separate files
- Related items can be grouped — if several entries are about the same topic, combine them into one file with sections
- Keep the original language of the content (don't translate)
- Preserve the user's tone and wording; light formatting is okay (e.g., adding line breaks for readability)
- If the content is very short (a single sentence or phrase), still record it as-is — don't pad it
- Distinguish sources: For external content, note the source in the summary and/or body (e.g.,
(source: Hacker News),(from a conversation with Alex)). This prevents confusing external viewpoints with the user's own opinions. - Don't over-capture: Only record when the user explicitly asks. Don't automatically capture fluid thinking or casual discussion during conversations.
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.
- 5d ago First seen · 167 lines · 1,499 tokens per session scan A 3633de4606fd
opennote CLAUDE.md is an instructions file published in the GitHub repository ryannli/opennote (23 stars, last pushed 5mo ago), licensed MIT. It adds 1,499 tokens to every session, about $0.0075 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 instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).