update

update is a command for Claude Code from restarter/lets-workflow. It costs 69 tokens per session (3,574 once invoked), scanned C, original, MIT.

A command for synchronising a LETS project with its current release, including environment files, rules, and optional tracking files. LETS is the project system being updated, and the command follows the next required step until versions match.

In plain words
What is it for?
Use it to refresh LETS configuration and rules, install the required binary when approved, and identify the remaining plugin or sync action.
Why use it?
It removes the manual work of finding version drift and deciding which update step comes next.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the lets plugin — 20 skills, 26 commands, 16 agents shipped together

Good fit Use it to refresh LETS configuration and rules, install the required binary when approved, and identify the remaining plugin or sync action.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add restarter/lets-workflow
Claude Code
/plugin install lets

Made for: Claude Code.

Or install lets, the plugin that ships this one along with the rest of its 20 skills, 26 commands, 16 agents.

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 update

README.md
[![agentmods](https://agentmods.dev/badge/commands/restarter/lets-workflow/update/github.svg)](https://agentmods.dev/commands/restarter/lets-workflow/update)
Your own site
<a href="https://agentmods.dev/commands/restarter/lets-workflow/update"><img src="https://agentmods.dev/badge/commands/restarter/lets-workflow/update/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 update

Your own site · 80×15
<a href="https://agentmods.dev/commands/restarter/lets-workflow/update"><img src="https://agentmods.dev/badge/commands/restarter/lets-workflow/update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,574 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00069 $0.03574
Opus 5.5 $0.00028 $0.01430
Sonnet 5.5 $0.00014 $0.00715
Haiku 4.5 $0.00007 $0.00357

Measured 22d ago against content hash c12ff6737315, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

update scanned grade C with 2 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 22d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- `NO_LETS_BINARY` → tell user: "`lets` binary not found on `$PATH`. Install it — `! curl -fsSL https://raw.githubusercontent.com/restarter/lets-workflow/main/scripts/install.sh | bash` (the leading `!` runs it in this s

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `NO_LETS_BINARY` → tell user: "`lets` binary not found on `$PATH`. Install it — `! curl -fsSL https://raw.githubusercontent.com/restarter/lets-workflow/main/scripts/install.sh | bash` (the leading `!` runs it in this s
plugins/lets/commands/update.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update LETS

Sync the drift-able LETS artifacts (four core + two optional: the user-scope global rules and the active tracker-<name>.md adapter) with the current release. Bridges to lets update --json (Go binary): auto-syncs .lets/.env (header refresh when LETS_ENV_VERSION is stale), .claude/rules/lets-rules.md (re-copy when outdated/missing - but deferred when the plugin is behind, so rules never sync to a stale plugin), and reports ~/.claude/rules/lets-rules.md (the global rules - maintained by the session hook as a cache of the running plugin, only reported here, never written; the user-rules row appears only when that file exists). It then computes a single ordered next_action (the self-driving loop): the binary and plugin steps can be run in-session (approval-gated), and a fully-synced machine prints ✓ Everything on vX.Y.Z.

MANDATORY: Execute every Step's bash block literally as written. Do not substitute output from earlier ls/cat in this conversation - .env and other dotfiles are invisible to plain ls. The test -f checks below ARE the contract.

Difference from /lets:init: /lets:init is first-time setup (it also asks config questions and sets up the statusline + beads). /lets:update only syncs what a new release changes - it asks no project-configuration questions and never touches settings.json or beads; the binary install and the on-disk plugin refresh each run only after an approval prompt.

Step 1: Pre-checks

command -v lets >/dev/null 2>&1 || { echo "NO_LETS_BINARY"; exit 0; }
LETS_PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null) || { echo "NOT_GIT_REPO"; exit 0; }
test -f "$LETS_PROJECT_ROOT/.lets/.env" && echo "ENV_EXISTS" || echo "ENV_ABSENT"

Branch on output:

  • NO_LETS_BINARY → tell user: "lets binary not found on $PATH. Install it — ! curl -fsSL https://raw.githubusercontent.com/restarter/lets-workflow/main/scripts/install.sh | bash (the leading ! runs it in this session; or the same command without ! in a terminal). See the README → Quick Start." NO LETS box. STOP.
  • NOT_GIT_REPO → tell user: "Not a git repository. /lets:update runs inside a LETS project." NO LETS box. STOP.
  • ENV_ABSENT → not initialized. Tell user: "This project hasn't been set up - run /lets:init first." Then still run Step 2 (it reports .env: not-initialized plus the binary/plugin status, which is useful). In Step 4 show the LETS box pointing at /lets:init instead of /lets:start.
  • ENV_EXISTS → normal path. Continue to Step 2.

Read the full file on GitHub · 171 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. 22d ago Changed · +44 lines · +14 tokens per session c12ff6737315
  2. 1mo ago First seen · 127 lines · 55 tokens per session scan C 743328181c5d

Subscribe to this mod's changes

update is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 3,574 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.