wrapping-up-a-piece

wrapping-up-a-piece is a skill for Claude Code from redhuntlabs/wizard. It costs 32 tokens per session (1,020 once invoked), scanned A, original, MIT.

A closing workflow for completed work, covering handoff, archiving, and recording follow-up items. A handoff passes the result and important context to the next person or future you.

In plain words
What is it for?
Use it when a project, milestone, or task is done, especially before handing it to someone else, taking time off, or switching context.
Why use it?
It helps prevent finished work from being forgotten, poorly handed over, or reopened because deferred tasks and useful context were not recorded.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wizard plugin — 37 skills, 6 commands, 1 agent, 1 hook shipped together

Good fit Use it when a project, milestone, or task is done, especially before handing it to someone else, taking time off, or switching context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhuntlabs/wizard/wrapping-up-a-piece
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 redhuntlabs/wizard --skill wrapping-up-a-piece
Clone the repo
git clone --depth 1 https://github.com/redhuntlabs/wizard

Made for: Claude Code.

Or install wizard, the plugin that ships this one along with the rest of its 37 skills, 6 commands, 1 agent, 1 hook.

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 wrapping-up-a-piece

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhuntlabs/wizard/wrapping-up-a-piece/github.svg)](https://agentmods.dev/skills/redhuntlabs/wizard/wrapping-up-a-piece)
Your own site
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/wrapping-up-a-piece"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/wrapping-up-a-piece/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 wrapping-up-a-piece

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/wrapping-up-a-piece"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/wrapping-up-a-piece.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,020 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 $0.00032 $0.01020
Opus 5 $0.00016 $0.00510
Sonnet 5 $0.00006 $0.00204
Haiku 4.5 $0.00003 $0.00102

Measured 10d ago against content hash 1d425ff63f03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wrapping-up-a-piece 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 10d 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.

spells/work/wrapping-up-a-piece/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrapping Up a Piece

What this does

Runs a structured closing pass on a piece of work: handoff, archive, follow-up. Distinct from verifying-before-shipping (which is "is this done?"). This is "now that it's done, what closes it for good?"

When to use

  • A project, milestone, or task has reached "done" status
  • You're handing off work to someone else
  • You're closing out before time off or a context switch
  • You want to prevent the work from boomeranging back

What you bring (Inputs)

  • The finished piece of work
  • Who else is affected (handoff target, downstream consumers, future-you)
  • Whether anything was deferred from this piece

What you get (Output)

A clean closure: handoff message sent, artifacts archived, deferrals captured, retrospective if warranted.

How it works (Steps)

This is a workflow.

Stages

Stage 1: Handoff

Identify who needs the work next (or who needs to know it's done). Send them: a one-line summary, a link to the artifact, a one-line "what they should know" note.

Stage 2: Archive

Put the artifact where future-you (or future-them) will find it. Include a one-paragraph context note: why the work happened, what it solved, who decided what.

Stage 3: Capture deferrals

What did you cut from scope, push to next time, or punt? Write each as a ticket / todo / note with enough context that someone (or you in 3 months) could pick it up cold.

Stage 4: Retrospective (if warranted)

For pieces over 1 week of work, write 3 lines: what went well, what didn't, what you'd do differently. Even just for yourself.

Stage 5: Tell the world (optionally)

If someone external benefits from knowing this is done (a customer, a partner, a stakeholder), send the message. Brief, references the artifact, names what changes for them.

Stage 6: Close the file

Mark the ticket / project / doc closed. Resist re-opening for "one more thing" — that goes in deferrals.

Checkpoints

  • After Stage 1: handoff sent (or explicitly "no handoff needed")
  • After Stage 2: artifact has a context note (not just a file link)
  • After Stage 3: every deferral is captured somewhere retrievable
  • After Stage 4: retro written for substantial pieces
  • After Stage 5: external comms sent (if applicable)
  • After Stage 6: project state changed to closed

Read the full file on GitHub · 105 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. 10d ago First seen · 105 lines · 32 tokens per session scan A 1d425ff63f03

Subscribe to this mod's changes

wrapping-up-a-piece is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,020 once invoked, about $0.0002 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.