note

A command for adding progress notes, decisions, and context to the active coding task. It can also save a detailed resume note before the conversation is shortened.

In plain words
What is it for?
Use it to record updates, decisions, context, or a recovery summary before compaction.
Why use it?
It keeps important task information available during longer work or when handing work back to a later session.

Command

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.

agentmods
npx agentmods add commands/restarter/lets-workflow/note
Clone the repo
git clone --depth 1 https://github.com/restarter/lets-workflow
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.01603
Opus 5 $0.00014 $0.00801
Sonnet 5 $0.00006 $0.00321
Haiku 4.5 $0.00003 $0.00160

Measured 2d ago against content hash e8b436e9dd1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

note 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 2d 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.

plugins/lets/commands/note.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Note

Add a note to the active task. For mid-work documentation - progress updates, research findings, decisions, context for future sessions.

This is a utility, not a flow step. Main flow handles documentation automatically:

  • /lets:commit records commits to the task
  • /lets:done documents task completion
  • /lets:end saves session progress

Use /lets:note when you want to add extra context that doesn't fit those flows.

IMPORTANT: If the spec below invokes any deferred tool (e.g. AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.

Usage

/lets:note                  # interactive - pick a note type, add to the active task
/lets:note <free text>      # use the text directly as the note (infer type)
/lets:note --pre-compact    # RESUME snapshot of the whole session before /compact

Step 0: Argument Parsing

If --pre-compact (alias --compact) is passed -> run Pre-Compact Resume Mode (below) INSTEAD of Steps 3-4: no type prompt, produce ONE recovery-grade snapshot. Do NOT run Step 1's interactive task prompt - the session-snapshot skill owns task detection (file-primary: ambiguity -> file only, no prompt), keeping this byte-identical to /lets:end --pre-compact. Then show the Pre-Compact output below, NOT the generic Output box (no separate verify - the skill returns the path + task id, and /lets:end --pre-compact likewise just delegates and stops).

Otherwise -> normal flow (Steps 1-6).

When to Use

  • Research findings: "Investigated X, found Y"
  • Design decisions: "Chose approach A because..."
  • Blocker discovered: "Can't proceed until Z"
  • Context dump: "Important info for next session"

Step 1: Active Task Detection

Use the detect-task skill to find the active task: Skill(skill: "lets:detect-task"). If no active task or multiple tasks found - ask user which task to add a note to.

Read the full file on GitHub · 185 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.

  1. 2d ago First seen · 185 lines · 28 tokens per session scan A e8b436e9dd1a

Subscribe to this mod's changes

note is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 28 tokens to every session and 1,603 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 2026-08-30.