Managed Agent Wrap-Up

Wrap-up — close it out

by alirezarezvani · MIT license · ★ 26,349 on GitHub · v2.11.2 · updated Aug 30

Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says "wrap up", "close this out", "what do I own…

---
name: wrap-up
description: Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says "wrap up", "close this out", "what do I own now", "give me the summary", "recap the agent", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained ./my-agent/agent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.
version: 2.11.2
author: Alireza Rezvani
license: MIT
tags: [cma, wrap-up, closeout, inventory, overview, upgrades, next-directions]
compatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]
---

# Wrap-up — close it out

The explicit close-out. Confirm what's live, regenerate the shareable overview,
and name the next 1–2 upgrades so the founder leaves with a clear roadmap. The
`./my-agent/` folder keeps working after the session ends.

## Workflow

Overview

The explicit close-out. Confirm what's live, regenerate the shareable overview, and name the next 1–2 upgrades so the founder leaves with a clear roadmap. The ./my-agent/ folder keeps working after the session ends.

Manual install (npx, ZIP)

Claude Codenpx skills add alirezarezvani/claude-skills --skill wrap-up -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/alirezarezvani/claude-skills/tar.gz/19392f7a0826 \
  | tar -xz -C ~/.claude/skills --strip-components=3 claude-skills-19392f7a0826/agent-launcher/skills/wrap-up

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/a7127ec0da76d8bd577a/wrap-up.zip" -OutFile "$env:TEMP\wrap-up.zip"; Expand-Archive "$env:TEMP\wrap-up.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md3.0 KB
README.md844 B
scripts/3 files · 12.3 KB

Read the files here

alirezarezvani/19392f75 files

SKILL.md

Show the full text64 lines

wrap-up/SKILL.md64 lines · 3.0 KB

PreviewCode

Outline

RawView on GitHub

Wrap-up — close it out

The explicit close-out. Confirm what's live, regenerate the shareable overview, and name the next 1–2 upgrades so the founder leaves with a clear roadmap. The ./my-agent/ folder keeps working after the session ends.

Workflow

Inventory what they own.
```
python3 scripts/primitives_inventory.py \
  --sheet ./my-agent/build-sheet.json --goal ./my-agent/goal.json
```
Tables agent / environment / session / memory / outcome / deployment and the phases completed.

Regenerate the overview page.

python3 scripts/overview_page.py \
  --sheet ./my-agent/build-sheet.json --out-dir ./my-agent \
  --status live --loop-shape cron-loop --last-verdict satisfied

Self-contained agent-overview.html (inline CSS, theme-aware, no external assets) — shareable as-is.

Suggest the next moves.
```
python3 scripts/upgrade_suggester.py --sheet ./my-agent/build-sheet.json --top 2
```
Ranks recorded deferrals (v1 before v2, real-integration first) plus standing hardening (tighten networking, pin the agent version, nest an outcome).
Finalize. Ensure NEXT-DIRECTIONS.md is current (Phase-4 tool), then goal_state.py advance → phase=done.

Hard rules

Recap what's actually live — read it from the sheet + goal state, never assert primitives that weren't created.
The overview is single-file — no external assets, so it shares cleanly.
Every next move names the exact mechanism.

"Confirm what's live vs still a plan?" Recommend: inventory from the sheet. Cite: this SKILL.
"Which single upgrade has the highest payoff?" Recommend: the top-ranked v1 deferral. Cite: upgrade_suggester ranking.
"Is the overview page current?" Recommend: regenerate after any change. Cite: this SKILL.

Tools

scripts/primitives_inventory.py — recap every owned primitive.
scripts/overview_page.py — regenerate single-file agent-overview.html.
scripts/upgrade_suggester.py — next 1–2 upgrades with mechanisms.

1	---
2	name: wrap-up
3	description: Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says "wrap up", "close this out", "what do I own now", "give me the summary", "recap the agent", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained ./my-agent/agent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.
4	version: 2.11.2
5	author: Alireza Rezvani
6	license: MIT
7	tags: [cma, wrap-up, closeout, inventory, overview, upgrades, next-directions]
8	compatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]
9	---
10
11	# Wrap-up — close it out
12
13	The explicit close-out. Confirm what's live, regenerate the shareable overview,
14	and name the next 1–2 upgrades so the founder leaves with a clear roadmap. The
15	`./my-agent/` folder keeps working after the session ends.
16
17	## Workflow
18
19	1. Inventory what they own.
20	```bash
21	python3 scripts/primitives_inventory.py \
22	--sheet ./my-agent/build-sheet.json --goal ./my-agent/goal.json
23	```
24	Tables agent / environment / session / memory / outcome / deployment and the
25	phases completed.
26	2. Regenerate the overview page.
27	```bash
28	python3 scripts/overview_page.py \
29	--sheet ./my-agent/build-sheet.json --out-dir ./my-agent \
30	--status live --loop-shape cron-loop --last-verdict satisfied
31	```
32	Self-contained `agent-overview.html` (inline CSS, theme-aware, no external
33	assets) — shareable as-is.
34	3. Suggest the next moves.
35	```bash
36	python3 scripts/upgrade_suggester.py --sheet ./my-agent/build-sheet.json --top 2
37	```
38	Ranks recorded deferrals (v1 before v2, real-integration first) plus standing
39	hardening (tighten networking, pin the agent version, nest an outcome).
40	4. Finalize. Ensure `NEXT-DIRECTIONS.md` is current (Phase-4 tool), then
41	`goal_state.py advance` → `phase=done`.
42
43	## Hard rules
44
45	- Recap what's actually live — read it from the sheet + goal state, never
46	assert primitives that weren't created.
47	- The overview is single-file — no external assets, so it shares cleanly.
48	- Every next move names the exact mechanism.
49
50	## Forcing-question library (recommend + cite)
51
52	1. "Confirm what's live vs still a plan?" Recommend: inventory from the sheet.
53	Cite: this SKILL.
54	2. "Which single upgrade has the highest payoff?" Recommend: the top-ranked v1
55	deferral. Cite: upgrade_suggester ranking.
56	3. "Is the overview page current?" Recommend: regenerate after any change.
57	Cite: this SKILL.
58
59	## Tools
60
61	- `scripts/primitives_inventory.py` — recap every owned primitive.
62	- `scripts/overview_page.py` — regenerate single-file agent-overview.html.
63	- `scripts/upgrade_suggester.py` — next 1–2 upgrades with mechanisms.
64