agentmods.dev

wrap-up

wrap-up is a skill for Claude Code from tianhanz/ears. It costs 126 tokens per session (2,499 once invoked), scanned A, original, MIT.

A feature-branch finishing tool that reviews changes, updates relevant documentation, commits work, merges it into the main branch, and can optionally push it.

In plain words
What is it for?
Use it to finish a feature branch, inspect its changes, create a properly named commit, merge it, and report the result.
Why use it?
It organizes the final steps that are easy to forget when a feature is ready, such as documentation, commits, and integration with the main branch.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/check_invariants.py.

not rated 6repo 6mo ago A scan 126 tokens original MIT

Good fit Use it to finish a feature branch, inspect its changes, create a properly named commit, merge it, and report the result.

Compare 6 skills from other repositories ↓
View source ↗ tianhanz/ears
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tianhanz/ears
agentmods
npx agentmods add skills/tianhanz/ears/wrap-up

Made for: Claude Code.

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/tianhanz/ears/wrap-up/github.svg)](https://agentmods.dev/skills/tianhanz/ears/wrap-up)
Your own site
<a href="https://agentmods.dev/skills/tianhanz/ears/wrap-up"><img src="https://agentmods.dev/badge/skills/tianhanz/ears/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/tianhanz/ears/wrap-up"><img src="https://agentmods.dev/badge/skills/tianhanz/ears/wrap-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,499 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 $0.00126 $0.02499
Opus 5.5 $0.00050 $0.01000
Sonnet 5.5 $0.00025 $0.00500
Haiku 4.5 $0.00013 $0.00250

Measured 2mo ago against content hash 4a49ea8907b4, 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 2mo 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.

skills/wrap-up/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrap Up Feature Branch

Finalize the current feature branch by discovering what changed, updating relevant documentation, committing, merging, and reporting.

The argument provided is: $ARGUMENTS

Step 1 — Understand the current state

  1. Run git branch --show-current to get the current branch.

    • If $ARGUMENTS names a different branch, use that.
    • If already on the main branch, abort: "Already on the main branch — nothing to merge."

  2. Determine the main branch name. Check which exists:

    git rev-parse --verify main 2>/dev/null && echo "main"
git rev-parse --verify master 2>/dev/null && echo "master"

    Use whichever resolves. If both exist, prefer main.

  3. List what this branch adds over main:

    git log --oneline <main>..<branch>
git diff --stat <main>..<branch>

    Show the commit list and changed-file summary to the user.

  4. Check for uncommitted work:

    git status
git diff --stat

    If there are unstaged or uncommitted changes, commit them first with a descriptive message matching the repo's style (check git log --oneline -5 for conventions).

Step 2 — Discover documentation to update

Do NOT assume any specific filenames. Instead, discover what exists:

  1. Find all markdown files in the repo:

    find . -name '*.md' -not -path './.git/*' | sort

  2. Find all HTML files that look like reports or summaries (not application code):

    find . -name '*.html' -not -path './.git/*' -not -path '*/node_modules/*' | sort

  3. From these lists, identify documentation files that are likely candidates for update. Look for files whose names or content suggest they track:

    • Project status, progress, or implementation state
    • Summaries or overviews of what the project contains
    • Reports (especially HTML reports with timestamps)
    • READMEs at any level (root, subdirectories)

  4. Read each candidate file to understand its purpose and current content. Decide whether the branch's changes warrant an update to that file:

    • Does the file reference features, tools, cases, or components that this branch added/changed?
    • Does the file have a date or timestamp that should be refreshed?
    • Does the file have a summary table, status list, or directory tree that is now stale?

Read the full file on GitHub · 231 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. 2mo ago First seen · 231 lines · 126 tokens per session scan A 4a49ea8907b4

Subscribe to this mod's changes

wrap-up is a skill published in the GitHub repository tianhanz/ears (6 stars, last pushed 6mo ago), licensed MIT. It adds 126 tokens to every session and 2,499 once invoked, about $0.0005 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 2026-08-31.

CommitsGit and workflowWriting and docs
Related

wrap-up compared with skills from other repositories

wrap-up next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wrap-uptianhanz/earsSkill66mo agoMITA126Claude Code
create-prprisma/ormSkill48ktodayApache-2.0A48Claude Code, Codex
git-commitThinkInAIXYZ/deepchatSkill6.4kyesterdayApache-2.0A15Claude Code, Codex
repo-syncdavidondrej/skillsSkill4.3kyesterdayMITA25Claude Code, Codex
engineer-bot-opsmakecindy/cindySkill9.4ktodayApache-2.0A57Claude Code, Codex
mcore-split-prNVIDIA/skillsSkill3.9ktodayApache-2.0A25Claude Code
git-commit-writermergisi/awesome-openclaw-agentsSkill4.1k3d agoMITA53Claude Code, Codex