wrapup

wrapup is a command for Claude Code from terrene-foundation/metis. It costs 20 tokens per session (1,236 once invoked), scanned A, original, Apache-2.0.

A command that records the important context from a coding session in a .session-notes file for the next session.

In plain words
What is it for?
It helps hand off work between sessions, record unreleased packages in build repositories, and point the next session toward remaining tasks.
Why use it?
It prevents the next coding session from spending time rediscovering decisions, findings, risks, and unfinished work.

Command for Claude Code

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/terrene-foundation/metis/wrapup
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

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.

agentmods badge for wrapup

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/metis/wrapup.svg)](https://agentmods.dev/commands/terrene-foundation/metis/wrapup)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/metis/wrapup"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/wrapup.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,236 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 $0.00020 $0.01236
Opus 5 $0.00010 $0.00618
Sonnet 5 $0.00004 $0.00247
Haiku 4.5 $0.00002 $0.00124

Measured 4d ago against content hash c4537d49473a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wrapup 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 4d 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/commands/wrapup.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The only deliverable is a .session-notes file that lets a fresh session start producing work within 2–3 minutes of reading it, without having to re-explore the codebase.

Before running: if significant decisions, discoveries, or risks from this session are not yet in journal/, run /journal new DECISION|DISCOVERY|RISK <topic> first. .session-notes is not a decision log.

Release drift check (MUST — BUILD repos only): Before writing .session-notes, run node .claude/hooks/lib/release-drift.js via a quick inline check (or inspect the [RELEASE-DRIFT] lines from session-start). If any packages have commits since their last tag, surface this to the user with a recommendation to run /release before ending the session. Record the unreleased package list in .session-notes under an "Unreleased packages" section so the next session sees the backlog. Silent on downstream repos / non-package repos.

What the next session already has for free

Do NOT duplicate these — the next session reads them directly:

  • Commits & diffsgit log, git status, git diff
  • Outstanding workworkspaces/<project>/todos/active/
  • Decisions & discoveriesworkspaces/<project>/journal/
  • Phase outputs01-analysis/, 02-plans/, 03-user-flows/, 04-validate/
  • Domain specsspecs/ (detailed domain truth, always current)
  • Project contextCLAUDE.md

What ONLY wrapup can provide

Three things nothing else captures:

  1. Priority ordering — out of everything in the repo, which files should the next session read first, and in what order
  2. In-flight state — what's true RIGHT NOW that isn't yet committed, journaled, or filed as a todo
  3. Traps — specific pitfalls the next session will walk into without warning

If content doesn't fit one of those three, it belongs somewhere else. Put it there before running /wrapup.

Where to write

  1. If $ARGUMENTS names a workspace, write workspaces/$ARGUMENTS/.session-notes
  2. Else use the most recently modified directory under workspaces/ (excluding instructions/)
  3. Else write .session-notes at the repo root

Read the full file on GitHub · 92 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. 4d ago First seen · 92 lines · 20 tokens per session scan A c4537d49473a

Subscribe to this mod's changes

wrapup is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,236 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.