catch-me-up

catch-me-up is a command for Claude Code from openshift-eng/ai-helpers. It costs 14 tokens per session (1,752 once invoked), scanned A, original, Apache-2.0.

A Jira command that reviews recent activity on issues you follow or own and sorts events into needs attention, unsure, or noise.

In plain words
What is it for?
Use it for a daily or weekly Jira check-up covering recent comments, status changes, and other activity from a chosen time period.
Why use it?
It reduces the effort of checking many Jira updates and filters out changes that do not require action.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 plugins/jira/skills/catch-me-up/scripts/split_batches.py .work/catch-me-up/runs/<date>-<days>d/events.json 5.

Part of the jira plugin — 13 skills, 17 commands shipped together

Good fit Use it for a daily or weekly Jira check-up covering recent comments…

Compare 6 commands from other repositories ↓
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/openshift-eng/ai-helpers
agentmods
npx agentmods add commands/openshift-eng/ai-helpers/catch-me-up

Made for: Claude Code.

Or install jira, the plugin that ships this one along with the rest of its 13 skills, 17 commands.

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 catch-me-up

README.md
[![agentmods](https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/catch-me-up.svg)](https://agentmods.dev/commands/openshift-eng/ai-helpers/catch-me-up)
Your own site
<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/catch-me-up"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/catch-me-up.svg" alt="Measured on agentmods" height="20"></a>
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 1,752 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 $0.00014 $0.01752
Opus 5 $0.00007 $0.00876
Sonnet 5 $0.00003 $0.00350
Haiku 4.5 $0.00001 $0.00175

Measured 3d ago against content hash 53db8c335a14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

catch-me-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 3d 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.

plugins/jira/commands/catch-me-up.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Name

jira:catch-me-up

Synopsis

/jira:catch-me-up [14] [--days 7] [--no-cache]

Description

Fetches recent activity on Jira issues where you are assignee or watcher, then classifies each event into three tiers: needs attention, unsure, or noise. Uses a map/reduce approach — fast model classifies batches in parallel, then a review pass catches cross-event patterns.

Prerequisites

  • JIRA_API_TOKEN and JIRA_USERNAME environment variables set
  • uv (astral.sh/uv) — the gather script is run via uv run --with aiohttp
  • JIRA_URL defaults to https://redhat.atlassian.net

Implementation

Step 1: Parse arguments

Default --days to 7 if not specified. The user may pass a number directly (e.g., /jira:catch-me-up 14 means 14 days).

Step 2: Check subagent permissions

Read .claude/settings.local.json. If the file exists, check whether Read(.work/catch-me-up/**) is in the permissions.allow array.

If present, continue silently.

If missing (or the file doesn't exist), append Read(.work/catch-me-up/**) to the permissions.allow array. Preserve all existing content — only add this one entry. Tell the user:

Added Read(.work/catch-me-up/**) to .claude/settings.local.json — subagents need this to read batch files.

Step 3: Gather data

Run the data gathering script. Use uv run to handle the aiohttp dependency automatically.

uv run --with aiohttp plugins/jira/skills/catch-me-up/scripts/gather.py --days <N> -v --output-dir .work/catch-me-up/runs

If the user passed --no-cache, append --no-cache to the command above.

Check the output stats. If there are 0 events, tell the user and stop. Read the output file path from stderr.

Step 4: Split into batches

python3 plugins/jira/skills/catch-me-up/scripts/split_batches.py .work/catch-me-up/runs/<date>-<days>d/events.json 5

This creates batch files and prints a JSON manifest with batch_files paths.

Step 5: Classify batches in parallel

Read the full file on GitHub · 172 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. 3d ago First seen · 172 lines · 14 tokens per session scan A 53db8c335a14

Subscribe to this mod's changes

catch-me-up is a command published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,752 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 2026-09-03.