wrapup-skillup

A command that creates a report about an AI coding session, including lessons, tools used, problems, results, and possible future extensions. It saves the report as a dated Markdown file.

In plain words
What is it for?
Use it at the end of a session to document the original request, tool usage, lessons, pitfalls, outcomes, and references to tickets or issues.
Why use it?
It turns a session's scattered decisions and discoveries into a record that can be reviewed or reused later.

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/nodnarbnitram/claude-code-extensions/wrapup-skillup
Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,004 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 $0.00014 $0.01004
Opus 5 $0.00007 $0.00502
Sonnet 5 $0.00003 $0.00201
Haiku 4.5 $0.00001 $0.00100

Measured 2d ago against content hash 2a717f77a678, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wrapup-skillup 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 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.

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/wrapup-skillup.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Wrapup & Skillup

Generate a session report for topic: $ARGUMENTS

Your Task

Analyze this conversation session and create a comprehensive report that captures learnings, documents pitfalls, and recommends extensions that could help in future similar sessions.

Instructions

  1. Analyze the session context - Review the entire conversation from start to finish
  2. Extract the original request - Identify the first user message that started this session
  3. Summarize tool usage - Document which tools were used, how, and why
  4. Identify key learnings - What discoveries, patterns, or insights emerged?
  5. Document pitfalls - What problems were encountered? How were they resolved?
  6. Note outcomes - What was accomplished?
  7. Find ticket references - Look for any Linear, GitHub, or other ticket IDs mentioned
  8. Recommend extensions - Based on the session, suggest which extension types would be most valuable

Output Format

Write the report to: .claude/session-reports/YYYY-MM-DD-HH-MM-{topic}.md

Where {topic} is the topic-slug argument (use "session" if not provided).

Use this template structure:

# Session Report: {Topic Title}

## Metadata
- **Date**: YYYY-MM-DD HH:MM
- **Duration**: ~X minutes (estimate based on conversation length)
- **Related Tickets**: [ticket-ids or "None"]

## Original Request

> [Quote the first user message that initiated this session]

## Tools Used

| Tool | Purpose | Key Usage |
|------|---------|-----------|
| Tool1 | Why it was used | How it was applied |
| Tool2 | Why it was used | How it was applied |

## Key Learnings

- **Learning 1**: Description of what was discovered
- **Learning 2**: Description of pattern identified
- **Learning 3**: Description of insight gained

## Pitfalls & Solutions

### Pitfall: [Issue Name]
- **Problem**: What went wrong or was difficult
- **Solution**: How it was resolved
- **Prevention**: How to avoid this in the future

### Pitfall: [Another Issue]
- **Problem**: Description
- **Solution**: Resolution
- **Prevention**: Future avoidance strategy

## Results & Outcomes

- **Outcome 1**: What was accomplished
- **Outcome 2**: What was delivered
- **Files Changed**: List key files created or modified

## Extension Recommendations

Based on this session, the following extensions would help in similar future work:

### Recommended: [Skill/Command/Hook/Agent]

**Name**: `suggested-name`

**Purpose**: Why this extension would be valuable

**Type Justification**: Why this type (skill vs command vs hook vs agent) is appropriate

**Template**:
```yaml
---
name: suggested-name
description: Description for discovery
---

Read the full file on GitHub · 142 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 · 142 lines · 14 tokens per session scan A 2a717f77a678

Subscribe to this mod's changes

wrapup-skillup is a command published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,004 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 2026-08-30.