catch-me-up-on-a-thread

catch-me-up-on-a-thread is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 62 tokens per session (652 once invoked), scanned A, original, MIT.

A conversation summarizer that condenses a long customer thread into its current status, promises made, and what the customer is waiting for.

In plain words
What is it for?
Use it to catch up on a dormant or lengthy support thread, especially before drafting a reply.
Why use it?
It saves you from rereading a long message history before taking the next step.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to catch up on a dormant or lengthy support thread, especially before drafting a reply.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/catch-me-up-on-a-thread
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.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill catch-me-up-on-a-thread
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

Made for: Claude Code, Codex.

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-on-a-thread

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/catch-me-up-on-a-thread/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/catch-me-up-on-a-thread)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/catch-me-up-on-a-thread"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/catch-me-up-on-a-thread/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 catch-me-up-on-a-thread

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/catch-me-up-on-a-thread"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/catch-me-up-on-a-thread.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 652 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 $0.00062 $0.00652
Opus 5 $0.00031 $0.00326
Sonnet 5 $0.00012 $0.00130
Haiku 4.5 $0.00006 $0.00065

Measured 7d ago against content hash de8f794d5372, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

catch-me-up-on-a-thread 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 7d 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.

store/agents/support/.agents/skills/catch-me-up-on-a-thread/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Catch Me Up on a Thread

When to use

conversations/{id}/thread.json has >handful of messages, need context fast. Typical triggers:

  • You: "what's the story with the Acme thread?"
  • Reopen conversation dormant >3 days.
  • Before draft-a-reply on thread with 5+ messages - run first, draft better.

Connections I need

I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.

  • Inbox (Gmail / Outlook) - pull the live thread if it's not already in conversations.json. Optional.
  • Support helpdesk (Intercom / Zendesk / Help Scout) - alternate thread source. Optional.

I keep going against the local thread index if neither is connected, but I'll tell you the summary may be missing the latest reply.

Information I need

I read your support context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.

  • Which thread - Required. Why I need it: I summarize one specific conversation, not "support in general." If missing I ask: "Which conversation should I summarize - share the customer's name or the latest subject line?"
  • Audience for the summary - Optional. Why I need it: a 3-bullet for you reads differently than a handoff for a teammate. If you don't have it I keep going with TBD and write it for your eyes.

Steps

  1. Load conversations/{id}/thread.json and index row from conversations.json.
  2. Walk thread chronologically. Note: customer's original ask, scope changes, every promise made, every answer given.
  3. Produce exactly three bullets:
    • Where we are - last message, sender, current state (waiting on customer / waiting on us / drafting).
    • What we promised - outstanding commitments. Pull from followups.json filtered by conversation, plus uncaptured promises in thread (recommend track-my-promises if found).
    • What customer expects next - most recent explicit or implied ask.
  4. Append summary as dated block in conversations/{id}/notes.md - persisted for next time.

Read the full file on GitHub · 48 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. 7d ago First seen · 48 lines · 62 tokens per session scan A de8f794d5372

Subscribe to this mod's changes

catch-me-up-on-a-thread is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 62 tokens to every session and 652 once invoked, about $0.0003 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 2026-09-05.