What is letter-for-myself CLAUDE.md?

Repository instructions for the Letter to Myself Claude Code plugin, which saves summaries of coding sessions so work can continue later. They describe the plugin files and its process for turning saved notes into blog posts.

Use them when editing the plugin, its agents, skills, hooks, setup scripts, or the process that turns session notes into blog content.

They give the coding agent the project context and rules it needs to change the plugin safely. They also reduce the chance of losing track of work between sessions.

How nyxCore-Systems/letter-for-myself configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nyxCore-Systems/letter-for-myself. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nyxCore-Systems/letter-for-myself/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nyxCore-Systems/letter-for-myself

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nyxcore-systems/letter-for-myself/claude-md/github.svg)](https://agentmods.dev/instructions/nyxcore-systems/letter-for-myself/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nyxcore-systems/letter-for-myself/claude-md"><img src="https://agentmods.dev/badge/instructions/nyxcore-systems/letter-for-myself/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nyxcore-systems/letter-for-myself/claude-md"><img src="https://agentmods.dev/badge/instructions/nyxcore-systems/letter-for-myself/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,528 This file is loaded in full into every session.

When invoked 1,528 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01528	$0.01528
Opus 5	$0.00764	$0.00764
Sonnet 5	$0.00306	$0.00306
Haiku 4.5	$0.00153	$0.00153

Measured 9d ago against content hash a9de4174f6ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

letter-for-myself 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 9d 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.

CLAUDE.md · 153 lines

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.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Claude Code plugin called "Letter to Myself" that implements context persistence between Claude sessions. The plugin provides an agent and skill that automatically write structured "Last Will" summaries to a .memory/ folder, enabling seamless continuity when sessions end, get compacted, or when days pass between work sessions.

Core Components

Plugin Structure

.claude-plugin/plugin.json - Plugin manifest (v1.2.1) defining name, version, and component paths
.claude-plugin/marketplace.json - Marketplace listing metadata
agents/letter-for-myself.md - Agent persona that handles checkpoint creation
skills/letter-checkpoint/SKILL.md - Skill that writes memory checkpoints to disk
skills/letter-init/SKILL.md - Skill that sets up the Letter to Blog CI/CD pipeline
hooks/hooks.json - Plugin hooks (Setup and SessionStart)
scripts/setup-api-key.sh - First-time setup: installs agent/skills to ~/.claude/, prompts for API key
scripts/check-project-key.sh - Per-project initialization: creates directories, copies infrastructure, shows status
CLAUDE_TEMPLATE.md - Template users copy to their projects to enable the plugin
install_agents.sh - Legacy installation script that creates a nested plugin structure

Letter to Blog Pipeline (NEW)

The plugin now includes a "Letter to Blog" feature that automatically transforms memory files into public-ready blog posts:

.github/scripts/blog_gen.py - Python script using Anthropic API for blog generation
.github/scripts/vibe_requirements.txt - Python dependencies (anthropic, python-dotenv)
.github/workflows/vibe_publisher.yml - GitHub Actions workflow triggered on .memory/ changes
drafts/ - Output directory for generated blog posts

The Memory Protocol

Memory files are stored in .memory/ as timestamp-named markdown files (letter_YYYYMMDDHHMMSS.md)
Each file follows a strict template with sections: Executive Summary, Done List, Pain Log, Variable State, Next Steps
On startup, the agent reads the most recent letter file (sorted by timestamp) to restore context
On checkpoint/exit, the agent generates a new letter with current timestamp
Legacy formats (letter_YYYYMMDD_XXXX.md, letter_XX.md) are still supported for backwards compatibility

Read the full file on GitHub · 153 lines

Changes

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.

9d ago First seen · 153 lines · 1,528 tokens per session scan A a9de4174f6ea

Subscribe to this mod's changes

letter-for-myself CLAUDE.md is an instructions file published in the GitHub repository nyxCore-Systems/letter-for-myself (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,528 tokens to every session, about $0.0076 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

letter-for-myself: Instructions file for Claude Code