catchup

A command that helps you understand a project after clearing the chat or starting a new conversation.

In plain words
What is it for?
Use it after /clear or in a new chat to check template versions, read the README, inspect recent changes, and load relevant project records.
Why use it?
It gathers the project instructions, purpose, recent file changes, and recorded status so work can continue with context.

Command

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 commands/b33eep/claude-code-setup/catchup
Clone the repo
git clone --depth 1 https://github.com/b33eep/claude-code-setup
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 642 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 $0.00000 $0.00642
Opus 5 $0.00000 $0.00321
Sonnet 5 $0.00000 $0.00128
Haiku 4.5 $0.00000 $0.00064

Measured 2d ago against content hash 2a63999f5138, 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 2d 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.

commands/catchup.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Catchup: Understand Changed Files

After /clear or new chat, understand recent changes.

Tasks

  1. Check project template version

    • Read first line of project CLAUDE.md → extract version from <!-- project-template: N -->
    • If no marker found: treat as version 0
    • Use the Read tool on ~/.claude/templates/CLAUDE.template.md (expand ~ to absolute path) → extract version from first line
    • If file does not exist (Read returns error) → skip this step
    • If versions match → skip, continue to next task
    • If versions differ → use the Read tool on ~/.claude/commands/migrate-project-template.md (expand ~ to absolute path) → follow the migration steps inside
    • After migration completes → continue with step 2 (Read project README.md)
  2. Read project README.md

    • If exists: Read README.md in project root
    • Understand project purpose and structure
  3. Read changed files

    • If Git: git diff --name-only HEAD~10 (last 10 commits)
    • Or: git status for uncommitted changes
    • Read relevant changed files
  4. Load relevant Records

    • Check Current Status and Future tables in project CLAUDE.md
    • If work is in progress or a next step references a Record → Read that Record
    • Example: Status shows "OAuth2 | In Progress | [Record 019]" → Read docs/records/019-oauth2-auth.md
    • Also check for designs ready to implement or in progress:
      • grep -l "^Designing\|^Designed\|^In Progress" docs/records/*.md
    • If found: Load these Records (user may want to continue /design workflow or start implementing)
    • Only load Records relevant to current/next work, not all
  5. Check Recent Decisions

    • Read the "Recent Decisions" table in project CLAUDE.md
    • Note any decisions relevant to current work
    • These are small decisions with reasoning that survived the last /clear
  6. Read open private notes

    • Check for docs/notes/*.open.md files
    • If found: Read them (these are active session notes)
    • Summarize key points from open notes
    • These contain context from previous sessions (research, strategies, TODOs)

Read the full file on GitHub · 55 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. 2d ago First seen · 55 lines · 0 tokens per session scan A 2a63999f5138

Subscribe to this mod's changes

catchup is a command published in the GitHub repository b33eep/claude-code-setup (56 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 642 tokens. 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.