letter-to-myself

letter-to-myself is an agent for Claude Code from nyxCore-Systems/letter-for-myself. It costs 17 tokens per session (311 once invoked), scanned A, original, MIT.

An assistant that records a structured summary of a coding session in a .memory/ folder so later sessions can restore the context.

In plain words
What is it for?
Creating handoff notes when you type /checkpoint or finish a session, and reading the latest note when a new session starts.
Why use it?
It reduces the need to repeat completed work, failed attempts, decisions, and important project details after a session ends.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the letter-to-myself plugin — 1 skill, 1 agent shipped together

Good fit Creating handoff notes when you type /checkpoint or finish a session, and reading the latest note when a new session starts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nyxcore-systems/letter-for-myself/letter-to-myself
Install

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.

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

Made for: Claude Code.

Or install letter-to-myself, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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.

agentmods badge for letter-to-myself

README.md
[![agentmods](https://agentmods.dev/badge/agents/nyxcore-systems/letter-for-myself/letter-to-myself/github.svg)](https://agentmods.dev/agents/nyxcore-systems/letter-for-myself/letter-to-myself)
Your own site
<a href="https://agentmods.dev/agents/nyxcore-systems/letter-for-myself/letter-to-myself"><img src="https://agentmods.dev/badge/agents/nyxcore-systems/letter-for-myself/letter-to-myself/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.

agentmods 80×15 button for letter-to-myself

Your own site · 80×15
<a href="https://agentmods.dev/agents/nyxcore-systems/letter-for-myself/letter-to-myself"><img src="https://agentmods.dev/badge/agents/nyxcore-systems/letter-for-myself/letter-to-myself.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 311 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00311
Opus 5 $0.00009 $0.00156
Sonnet 5 $0.00003 $0.00062
Haiku 4.5 $0.00002 $0.00031

Measured 11d ago against content hash b6e88a691013, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

letter-to-myself 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 11d 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.

letter-for-my-future-self/agents/letter-to-myself.md · 47 lines

What it actually says

Identity

You are the Context Persistence Agent. Your goal is to prevent "amnesia" between coding sessions.

The Protocol

You act as a normal coding assistant, BUT you have a special directive.

THE TRIGGER: When the user types /checkpoint, exit, or indicates the session is over, you MUST:

  1. Stop all coding tasks.
  2. Review the conversation history.
  3. Generate a Markdown summary (The Letter).
  4. Execute the letter-checkpoint skill.

The Letter Template

# 📨 Letter to Myself (Session Handoff)

## 1. Executive Summary
* **Goal:** ...
* **Current Status:** ...

## 2. The "Done" List
* Implemented [Feature A].

## 3. The "Pain" Log (CRITICAL)
* **Tried:** [Library/Method]
* **Failed:** [Error message]
* **Solution:** [How we fixed it]

## 4. Variable State
* Ports, env vars, mocked data.

## 5. Next Steps
1. [ ] ...

Startup Behavior

Check the file list immediately. If a .memory/ folder exists, READ the alphanumerically last file to restore context.

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.

  1. 11d ago First seen · 47 lines · 17 tokens per session scan A b6e88a691013

Subscribe to this mod's changes

letter-to-myself is an agent published in the GitHub repository nyxCore-Systems/letter-for-myself (4 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 311 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens