rest

rest is a command for Claude Code from john-broadway/maude-for-claude. It costs 61 tokens per session (2,252 once invoked), scanned A, original, Apache-2.0.

A command for closing a coding session by creating a summary, recording the next starting point, and saving the results to configured memory locations.

In plain words
What is it for?
Use /maude:rest when wrapping up to save the session, check for open tasks, and write to registered network memory sources when allowed.
Why use it?
It reduces the chance of losing unfinished work or forgetting the next step when a session ends.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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 maude plugin — 1 skill, 15 commands, 1 agent, 8 hooks shipped together

Good fit Use /maude:rest when wrapping up to save the session, check for open tasks, and write to registered network memory sources when allowed.

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 john-broadway/maude-for-claude
Claude Code
/plugin install maude

Made for: Claude Code.

Or install maude, the plugin that ships this one along with the rest of its 1 skill, 15 commands, 1 agent, 8 hooks.

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 rest

README.md
[![agentmods](https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/rest/github.svg)](https://agentmods.dev/commands/john-broadway/maude-for-claude/rest)
Your own site
<a href="https://agentmods.dev/commands/john-broadway/maude-for-claude/rest"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/rest/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 rest

Your own site · 80×15
<a href="https://agentmods.dev/commands/john-broadway/maude-for-claude/rest"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/rest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,252 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 $0.00061 $0.02252
Opus 5 $0.00030 $0.01126
Sonnet 5 $0.00012 $0.00450
Haiku 4.5 $0.00006 $0.00225

Measured 8d ago against content hash f6fb1ddcdd7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rest 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 8d 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.

commands/rest.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/maude:rest

You are Maude. The user is wrapping up. Close the loop properly.

Tier discipline (writes — same as save, plus the network-OK clause)

  • Tier 0: ALWAYS write
  • Tier 0 SQLite: known schema + opt-in only
  • Tier 1: write if reachable
  • Tier 2: ALWAYS write to network sources registered as writable + auth set. Session-end is the right moment to pay the latency.
  • Tier 3: can't write

What to do

PROJ="${CLAUDE_PROJECT_DIR:-$(pwd)}"
SLUG="$(printf %s "$PROJ" | sed 's/[^a-zA-Z0-9]/-/g')"
MEM="$HOME/.claude/projects/$SLUG/memory"
SELF="$PROJ/.maude/plugin"
USER_DIR="$HOME/.claude/maude"
REMEMBER="$PROJ/.remember"
MAP="$SELF/house-map.md"
  1. Compose a digest of this session:

    • What got done?
    • What got decided?
    • What's still open?
    • Any half-finished work?
  2. Run the map-driven save loop — identical to /maude:save step 3: read $MAP and write the digest to each ## Memory sources entry per its tier gate × write: token (digest-fanout, handoff-only, full; skip read-only / secret-deny), honoring any journal/decisions/vault destinations the map records. Same fallback as save step 4 if the map is silent. Session-end adds the network clause: write Tier 2 sources too if registered writable + auth (latency is acceptable at session-end). Session-end is also the right moment to consolidate the user profile: if this session taught you something new about who you're working with (how they communicate, their rhythm, recurring focuses, the help they want), fold it into user-global identity.md — observed, never invented.

2b. Put the session on the tape. The digest goes to markdown; the durable half goes to the tape, and until this step runs the tape's buffer is empty and its rest loop consolidates nothing. Capture two kinds of thing, and nothing else:

  • His own words, where he said something that is still true tomorrow — a ruling, a correction, a standing preference. --authority user-verbatim (or user-paraphrase if you are compressing rather than quoting). These consolidate on their own, because writing down what he said is not a judgement call.
  • What you inferred — a maxim that fired, a trap that cost time, a pattern you noticed. Leave the default agent-inference. These will not become canon; they wait for /maude:promote. That is the point, not a limitation.

Read the full file on GitHub · 179 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. 8d ago First seen · 179 lines · 61 tokens per session scan A f6fb1ddcdd7d

Subscribe to this mod's changes

rest is a command published in the GitHub repository john-broadway/maude-for-claude (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,252 once invoked, about $0.0003 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.