wrapup

A session wrap-up command that records the current project status in CLAUDE.md before starting a new session. It also organizes completed work and important decisions.

In plain words
What is it for?
Use it before /clear to update status, next steps, project records, and development notes.
Why use it?
It gives the next session a clear starting point instead of relying on chat history.

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/b33eep/claude-code-setup/wrapup
Clone the repo
git clone --depth 1 https://github.com/b33eep/claude-code-setup
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 813 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00000 $0.00813
Opus 5 $0.00000 $0.00407
Sonnet 5 $0.00000 $0.00163
Haiku 4.5 $0.00000 $0.00081

Measured 2d ago against content hash 7b97e17dc655, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

wrapup scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

When updating CLAUDE.md, do not add, remove, or change any content between the `<!-- PROJECT INSTRUCTIONS START -->` and `<!-- PROJECT INSTRUCTIONS END -->` markers. Treat this section as read-only during /wrapup.
commands/wrapup.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrapup: Document and Restart

Wrap up the session before /clear. Document the current status for the next session.

Tasks

  1. Update CLAUDE.md

    • Update "Current Status" table (story status)
    • Update "Next Step" with clear next action
  2. Archive Done items

    • Remove rows with status "Done" from the Current Status table
    • Their history is preserved in git commits and Records
    • The Status table shows current work only (Open, In Progress)
  3. Prune Recent Decisions

    • Review the Recent Decisions table. Remove entries that are:
      • Implementation details already captured in a Record
      • Superseded by later decisions
      • Only relevant to a feature that's now Done
    • Keep only decisions that a future session (working on a different feature) might need
  4. Create Record (if needed)

    • Was a decision, design, or significant feature documented this session?
    • If yes: Create Record in docs/records/
    • Reference in Current Status or Future table if actively relevant
  5. Check: Development, Files, Architecture sections

    • Were commands added/changed this session? (new scripts, changed test commands, new build steps) → Update ## Development
    • Were files/directories added/removed/restructured? → Update ## Files
    • Were architectural changes made? (new patterns, changed data flow, new integrations) → Update ## Architecture
    • Only update if the session's work actually changed these. Don't rewrite for cosmetic reasons.
    • If a section contains only the template placeholder (text in {curly braces}), don't fill it in unless the session's work provides real content for it.
    • If a section doesn't exist yet in the project CLAUDE.md, skip it.
    • Keep updates concise — a few sentences or a short list. Detailed designs belong in Records.
  6. Review for missed decisions

    • Were any decisions made this session that are not in Recent Decisions?
    • A decision has: an alternative, a non-obvious "why", future relevance, project-level scope
    • If yes: Add them now (better late than never)
    • This is a safety net - decisions should be added in real-time

Read the full file on GitHub · 83 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 · 83 lines · 0 tokens per session scan C 7b97e17dc655

Subscribe to this mod's changes

wrapup is a command published in the GitHub repository b33eep/claude-code-setup (56 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 813 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.