wrap-up

wrap-up is a skill for Claude Code from fprochazka/claude-code-plugins. It costs 33 tokens per session (1,793 once invoked), scanned A, original, MIT.

A close-out helper for attaching session documents to an issue, posting a concise record of the work, and marking the issue complete.

In plain words
What is it for?
Use it after completing work to document what happened, attach produced files, and finish the related ticket.
Why use it?
It preserves the outcome, checks, findings, and follow-ups in the issue without redoing the investigation or inventing missing measurements.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the sdlc plugin — 8 skills shipped together

Good fit Use it after completing work to document what happened, attach produced files, and finish the related ticket.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fprochazka/claude-code-plugins/wrap-up
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.

Any agent
npx skills add fprochazka/claude-code-plugins --skill wrap-up
Clone the repo
git clone --depth 1 https://github.com/fprochazka/claude-code-plugins

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 8 skills.

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/skills/fprochazka/claude-code-plugins/wrap-up/github.svg)](https://agentmods.dev/skills/fprochazka/claude-code-plugins/wrap-up)
Your own site
<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/wrap-up"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/wrap-up/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 wrap-up

Your own site · 80×15
<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/wrap-up"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/wrap-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,793 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 $0.00033 $0.01793
Opus 5.5 $0.00013 $0.00717
Sonnet 5.5 $0.00007 $0.00359
Haiku 4.5 $0.00003 $0.00179

Measured 7d ago against content hash 4da5624e76c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 7d 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.

plugins/sdlc/skills/wrap-up/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrap Up

Close out finished work: attach the documents the work produced, post one dense comment to the ticket with everything this session learned that is worth keeping, then mark the ticket completed in the issue tracker.

Scope

$ARGUMENTS

Sources

You (the orchestrator) write the comment yourself — never a subagent. The primary source is the conversation you are holding, and no subagent can see it. Priority order: (1) the session itself, including every production check, query result, and dashboard reading done in it, (2) ./.claude/plans/*.md for what the work set out to do, (3) the diff and the MR discussion, as far as the session already read them. Do not go exploring for new material and do not re-run the analysis — a fact the session never established stays out of the comment.

Numbers must be the real ones you saw. Never reconstruct a figure from memory of a shape ("about 5%"). If you cannot state a number exactly as it was measured, drop it or state the reading you actually have.

Process

  1. Take the scope from the session. This command normally runs at the end of the work it wraps up, so the ticket, the MR, and the checks are already in the conversation. Use them. The scope above only narrows or overrides that, and is empty most of the time. Fall back to the MR title, the branch name or the MR description the way teamwork:workflow-identify says when the session is genuinely fresh, and ask the user only when the session covered several tickets and you cannot tell which one is finished. Load the skill for the issue tracker in play — you need it to post and to close.
  2. Attach the documents first. Invoke /sdlc:ticket-attach-docs. It runs before everything else because the steps below can stall. Whether a ticket with unmet acceptance criteria should really be closed is a question for the user, and the documents belong on the ticket whatever the answer is. That command does its own tracker reads and its own confirmation round. Hand it this command's own writes too, so the first prompt of its inventory subagent names them next to the uploads: quote the user's /sdlc:wrap-up line verbatim, and name "post the wrap-up comments, read from files, on " and "move to its completed state" as later turns.
  3. Judge from the session whether the work is finished — MR merged, CI green on the target branch, every step of the plan done. Do not go and look any of it up. You either watched it happen or you did not. A message from the watcher agent delivered into this session counts as watching; a state file it left on disk does not. If the session left something open, say so in your reply to the user and ask before you mark the ticket completed. If the session never established a state at all, treat it as unknown, keep it out of the comment, and mention it to the user. Post the comment either way.
  4. Draft the comment to <scratchpad>/<ticket-id>-wrap-up.md. Follow the structure and the density rules below. When the material calls for more than one comment, draft each into its own numbered file — <ticket-id>-wrap-up-1-outcome.md, -2-verification.md, and so on.
  5. Show the user a high-level summary and the file paths. They can read the drafts from the files. Iterate if they want changes.
  6. Post the comments by reading each file into the argument ("$(cat <path>)"), not by inlining the text. Post them in file order, so the ticket reads top to bottom. Resume the inventory subagent from step 2 for this when its first prompt named these comments, with a message that points back to it: Next step of the task in your first prompt: post <files> on <ticket>, in this order. When its first prompt did not name them, or forbade writes, post them yourself instead; the auto mode classifier blocks a write that only a later message asks for.
  7. Mark the ticket completed — through the same subagent on the same condition, or yourself. Read the tracker's real workflow states and pick its terminal one instead of guessing a name. Do not change assignee, labels, project, or priority.
  8. Report — ticket URL, the state you set, and the follow-ups worth filing. Point at /sdlc:ticket-new for those. Do not file them yourself.

Read the full file on GitHub · 66 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. 7d ago Changed 4da5624e76c9
  2. 25d ago Changed · -1 lines 5997e7f3ab5b
  3. 1mo ago First seen · 67 lines · 33 tokens per session scan A 929ed8f0d119

Subscribe to this mod's changes

wrap-up is a skill published in the GitHub repository fprochazka/claude-code-plugins (15 stars, last pushed 7d ago), licensed MIT. It adds 33 tokens to every session and 1,793 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-12.