catchup

catchup is a command for Claude Code from ThibautBaissac/rails_ai_agents. It costs 29 tokens per session (1,461 once invoked), scanned A, original, MIT.

A command that summarizes activity on the current Git branch since a developer last contributed. A Git branch is a separate line of development in a code repository.

In plain words
What is it for?
It helps report the branch, identify the returning developer, compare with the base branch, and summarize commits, authors, statistics, and important changes.
Why use it?
It helps someone returning to a branch understand what changed while they were away without reading every commit themselves.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit It helps report the branch, identify the returning developer, compare with the base branch, and summarize commits, authors, statistics, and important changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thibautbaissac/rails_ai_agents/catchup
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.

Clone the repo
git clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agents

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 catchup

README.md
[![agentmods](https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/catchup.svg)](https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/catchup)
Your own site
<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/catchup"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/catchup.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,461 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 $0.00029 $0.01461
Opus 5 $0.00015 $0.00731
Sonnet 5 $0.00006 $0.00292
Haiku 4.5 $0.00003 $0.00146

Measured 8d ago against content hash 52f2f9827966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

catchup 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 8d 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/catchup.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Catchup: Branch Activity Since Last Contribution

Produce a focused "welcome back" report for a developer returning to a feature branch, so they can catch up on what others (or they themselves) changed while they were away.

Input

$ARGUMENTS — optional identity of the returning developer:

  • empty → use the local git config user.email (and user.name)
  • an email → match commits by author.email
  • a name (or fragment) → match commits by author.name (case-insensitive)

Examples:

  • /catchup — catch up the current git user
  • /catchup [email protected] — catch up Alice by email
  • /catchup "Alice Martin" — catch up Alice by name

Workflow

  1. Resolve context — run, in parallel where possible:

    • git rev-parse --abbrev-ref HEAD → current branch (abort with a clear message if HEAD is detached or the branch is main/master).
    • git config user.email and git config user.name → default identity.
    • git remote show origin | sed -n 's/.*HEAD branch: //p' (fallback to main) → base branch.
    • git fetch --quiet if a remote exists, so comparisons use up-to-date refs. Skip silently on failure (offline).
  2. Resolve the developer:

    • Use $ARGUMENTS if provided; otherwise the local git identity.
    • Detect whether the argument looks like an email (contains @) to choose --author=<email> vs --author=<name>.
    • Record the resolved display string for the report header.
  3. Find the developer's last commit on this branch (merge-base scoped):

    git log <base>..HEAD --author="<dev>" -n 1 --format="%H %ci %s"
    
    • If a commit is found → use it as the since anchor (<sha>..HEAD).
    • If none → the dev has never committed on this branch. Use the branch divergence point as the anchor: git merge-base <base> HEAD. Flag this in the report as "first time on this branch".
  4. Gather activity between the anchor and HEAD (read-only commands only):

    • Commits with authors and dates: git log <anchor>..HEAD --format="%h|%an|%ae|%cr|%s" --no-merges
    • Author breakdown: git shortlog -sne <anchor>..HEAD --no-merges
    • Diff stats (files + lines): git diff --stat <anchor>..HEAD
    • Machine-readable per-file churn (for top-changed files): git diff --numstat <anchor>..HEAD
    • High-signal diffs for the top 3–5 most-changed files: git diff <anchor>..HEAD -- <path> (truncate each to the first ~200 lines of diff in the report; link the rest by filename).
    • Merge commits summary (if any), only listed — not expanded: git log <anchor>..HEAD --merges --format="%h %s"

Read the full file on GitHub · 120 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. 8d ago First seen · 120 lines · 29 tokens per session scan A 52f2f9827966

Subscribe to this mod's changes

catchup is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (659 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 1,461 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.