wrap-up

A wrap-up command for reviewing work at the end of a coding session and recording documentation, learnings, and unfinished actions.

In plain words
What is it for?
Use it to review staged and unstaged changes, inspect recent commit messages for lessons, update relevant documentation, and prepare for stopping or committing work.
Why use it?
It reduces the chance that important changes, discoveries, or follow-up tasks are forgotten before the session ends.

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/wittyreference/twilio-claude-plugin/wrap-up
Clone the repo
git clone --depth 1 https://github.com/wittyreference/twilio-claude-plugin
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,701 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 $0.00026 $0.01701
Opus 5 $0.00013 $0.00851
Sonnet 5 $0.00005 $0.00340
Haiku 4.5 $0.00003 $0.00170

Measured 2d ago against content hash 82361e1f213a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

commands/wrap-up.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Wrap-Up

Review the current session's work and update all relevant documentation before committing.

Steps

1. Gather Session Context

Collect what changed this session:

git diff --name-only HEAD  # unstaged + staged changes vs last commit
git diff --cached --name-only  # staged changes only

1b. Mine Commit Messages for Un-Captured Learnings

Check this session's commits for discovery signals that may not have been recorded:

# Get session start timestamp (check per-session file first, then legacy shared file)
SESSION_DIR={session-dir}
SESSION_START=$(ls -t "$SESSION_DIR"/.sessions/*.start 2>/dev/null | head -1 | xargs cat 2>/dev/null)
if [ -z "$SESSION_START" ]; then
    SESSION_START=$(cat "$SESSION_DIR/.session-start" 2>/dev/null)
fi
# List commits made this session
git log --since="@${SESSION_START}" --format='%h %s' 2>/dev/null

Scan commit subjects for learning signal words: fix, discover, gotcha, quirk, workaround, bug, edge case, actually, found that, regression, broken, issue.

For each flagged commit:

  1. Check if the topic already appears in the learnings file
  2. If not, flag it as a potential un-captured learning

Report flagged commits (if any) before proceeding to step 2:

Potential un-captured learnings from commits:
- abc1234: "fix: Verify FriendlyName rejects 5+ digits" -- not found in learnings

Skip this step if no commits were made this session or none match signal words.

2. Capture Learnings

Review the session's changes and identify anything worth recording:

  • Debugging insights or root causes discovered
  • API quirks or gotchas encountered
  • Patterns that worked (or didn't)
  • Configuration pitfalls

Add entries to .claude/learnings.md using the standard format:

## [YYYY-MM-DD] Topic

**Discoveries:**

1. **Finding**: What was learned
   - Context and details

If a learning is stable and broadly applicable, promote it directly to the target doc (CLAUDE.md, design docs, etc.) and note "Promoted to: [target]" in the learnings entry.

Read the full file on GitHub · 203 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 · 203 lines · 26 tokens per session scan A 82361e1f213a

Subscribe to this mod's changes

wrap-up is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,701 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 2026-08-31.