catchup

catchup is a skill for Claude Code, Codex from poshan0126/dotclaude. It costs 45 tokens per session (849 once invoked), scanned A, original, MIT.

A context-recovery tool for coding sessions. It reads a handoff note and recent branch changes so you can understand where work stopped after clearing the chat or starting a fresh session.

In plain words
What is it for?
Use it at the start of a session to catch up, or at the end to write a handoff note for the next session.
Why use it?
It avoids spending time reconstructing the current task, uncommitted work, and recent commits from scratch.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/poshan0126/dotclaude/catchup
Any agent
npx skills add poshan0126/dotclaude --skill catchup
Clone the repo
git clone --depth 1 https://github.com/poshan0126/dotclaude

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 catchup

README.md
[![agentmods](https://agentmods.dev/badge/skills/poshan0126/dotclaude/catchup.svg)](https://agentmods.dev/skills/poshan0126/dotclaude/catchup)
Your own site
<a href="https://agentmods.dev/skills/poshan0126/dotclaude/catchup"><img src="https://agentmods.dev/badge/skills/poshan0126/dotclaude/catchup.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00849
Opus 5 $0.00023 $0.00425
Sonnet 5 $0.00009 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 5d ago against content hash b50380ac05d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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/catchup/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Two modes. $ARGUMENTS containing handoff → write the handoff note (end of session). Anything else → catch up (start of session), treating any remaining arguments as a focus area.

Catch up (default)

Rebuild context in four steps, cheapest first. Read; never modify anything.

  1. Handoff note: if .claude/HANDOFF.md exists, read it first — it's the previous session's intent and beats anything inferable from git. Note its date; flag if it predates the latest commit (it may be stale).
  2. Branch state — live snapshot injected below (git output as of this session's start; no need to re-run these three):
BASE=$(git merge-base HEAD origin/HEAD 2>/dev/null || echo HEAD~10)
echo "### git status (uncommitted/staged work in flight)"
git status --short 2>/dev/null || echo "(not a git repo)"
echo
echo "### git log --oneline ${BASE}..HEAD (what this branch did)"
git log --oneline "${BASE}..HEAD" 2>/dev/null || echo "(no divergence from base)"
echo
echo "### git diff --stat ${BASE}..HEAD (where the change mass is)"
git diff --stat "${BASE}..HEAD" 2>/dev/null || echo "(no diff vs base)"
  1. Read the changed files — the diff hunks, not whole files. If more than ~15 files changed, read the 5 with the most churn plus anything matching the focus area, and list the rest by name.
  2. Summarize in this shape, terse:
## Catchup: <branch>

**Goal** (from handoff or inferred): <one line>
**Done**: <commits/changes, 2-4 bullets>
**In flight**: <uncommitted work, or "clean">
**Next** (from handoff, or inferred): <one line>
**Watch out**: <gotchas from the handoff, if any>

If there's no handoff note and no branch divergence (fresh clone, main at origin), say so and ask what to work on instead of inventing a summary.

Handoff (when $ARGUMENTS contains handoff)

Write .claude/HANDOFF.md capturing THIS session for the next one. Keep it under 30 lines — it's a note, not a transcript:

# Handoff — <date> — <branch>

## Goal
<what this work is trying to achieve, one line>

## State
- Done: <completed + verified>
- In flight: <started, not finished — exact file/function>
- Untouched: <known remaining scope>

## Gotchas
- <what failed and why, dead ends not to repeat, surprising constraints>

## Next step
<the single concrete action to take first>

Read the full file on GitHub · 79 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. 5d ago First seen · 79 lines · 45 tokens per session scan A b50380ac05d4

Subscribe to this mod's changes

catchup is a skill published in the GitHub repository poshan0126/dotclaude (860 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 849 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens