wrap-up

wrap-up is a command for Claude Code from hautc-it/cil. It costs 27 tokens per session (381 once invoked), scanned A, original, MIT.

An end-of-session command records what happened during a coding session and what should happen next.

In plain words
What is it for?
It is for creating a session summary, saving learnings and decisions, recording constraints, and noting the first task for the next session.
Why use it?
It prevents decisions, constraints, useful lessons, and unfinished work from being lost when the session ends.

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/hautc-it/cil/wrap-up
Clone the repo
git clone --depth 1 https://github.com/hautc-it/cil

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 wrap-up

README.md
[![agentmods](https://agentmods.dev/badge/commands/hautc-it/cil/wrap-up.svg)](https://agentmods.dev/commands/hautc-it/cil/wrap-up)
Your own site
<a href="https://agentmods.dev/commands/hautc-it/cil/wrap-up"><img src="https://agentmods.dev/badge/commands/hautc-it/cil/wrap-up.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 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 $0.00027 $0.00381
Opus 5 $0.00014 $0.00191
Sonnet 5 $0.00005 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 3d ago against content hash 170078b72480, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wrap-up 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 3d 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/wrap-up.md · 81 lines

What it actually says

/wrap-up

End-of-session protocol. Capture learnings before context is lost.


Step 1 — Summarize

What was accomplished this session? One paragraph, factual.


Step 2 — Capture learnings

For each insight from this session:

Questions to ask:

  • What worked well and should be repeated?
  • What was surprising, wrong, or unexpected?
  • What would you do differently next time?
  • What constraints were discovered?

Store each learning:

memory_store("learning", "[the insight]", ["relevant", "tags"])

What to store: decisions, constraints, architecture facts, discovered limitations, patterns that worked. Do NOT store: build errors, compile warnings, temporary bugs fixed during the session, tool output logs.


Step 3 — Capture decisions

For each architecture or design decision made:

memory_store("decision", "[what was decided] — [why]", ["component", "area"])

Step 4 — Capture constraints

For any constraint discovered (performance limits, API quirks, team rules):

memory_store("constraint", "[the constraint and where it applies]", ["area"])

Step 5 — Plan next session

  • What is unfinished?
  • What is the first task to pick up next time?

Store as task:

memory_store("task", "[next task description]", ["next-session"])

Step 6 — Housekeeping

git status

Flag any uncommitted work. Don't leave things dangling.

Create session snapshot:

session_snapshot("[session summary in 1-2 sentences]", ["decision1", "decision2"])
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. 3d ago First seen · 81 lines · 27 tokens per session scan A 170078b72480

Subscribe to this mod's changes

wrap-up is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 381 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.