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.
git clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agentsWrote 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.
[](https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/catchup)<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>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.
| Model | Per session | Once 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 |
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.
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(anduser.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
-
Resolve context — run, in parallel where possible:
git rev-parse --abbrev-ref HEAD→ current branch (abort with a clear message ifHEADis detached or the branch ismain/master).git config user.emailandgit config user.name→ default identity.git remote show origin | sed -n 's/.*HEAD branch: //p'(fallback tomain) → base branch.git fetch --quietif a remote exists, so comparisons use up-to-date refs. Skip silently on failure (offline).
-
Resolve the developer:
- Use
$ARGUMENTSif 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.
- Use
-
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".
- If a commit is found → use it as the since anchor (
-
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"
- Commits with authors and dates:
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.
- 8d ago First seen · 120 lines · 29 tokens per session scan A 52f2f9827966
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.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
handoff
Export a Waybill Bundle by default, or import one when requested.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.