scan

scan is a skill for Claude Code from xanoysky/catchup-claude-plugin. It costs 64 tokens per session (806 once invoked), scanned A, original, MIT.

A changelog reader that collects recent release notes from configured software projects and combines them into one short digest.

In plain words
What is it for?
Use it to catch up on changes to tools such as Claude Code, GitHub Copilot, OpenAI Codex, and OpenClaw, or to add and manage other changelog sources.
Why use it?
It removes the need to visit several project websites and read every update separately. You can also limit the digest to selected sources.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex; built for openclaw.

Part of the catchup plugin — 1 skill shipped together

Good fit Use it to catch up on changes to tools such as Claude Code, GitHub Copilot, OpenAI Codex, and OpenClaw, or to add and manage other changelog sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xanoysky/catchup-claude-plugin/scan
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 xanoysky/catchup-claude-plugin --skill scan
Clone the repo
git clone --depth 1 https://github.com/xanoysky/catchup-claude-plugin

Made for: Claude Code.

Or install catchup, the plugin that ships this one along with the rest of its 1 skill.

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 scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/xanoysky/catchup-claude-plugin/scan.svg)](https://agentmods.dev/skills/xanoysky/catchup-claude-plugin/scan)
Your own site
<a href="https://agentmods.dev/skills/xanoysky/catchup-claude-plugin/scan"><img src="https://agentmods.dev/badge/skills/xanoysky/catchup-claude-plugin/scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 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 $0.00064 $0.00806
Opus 5 $0.00032 $0.00403
Sonnet 5 $0.00013 $0.00161
Haiku 4.5 $0.00006 $0.00081

Measured 7d ago against content hash 8e5efdba9e7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

scan 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.

skills/scan/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Catchup

Fetches and summarizes recent changelogs into a single scannable digest.

Arguments

Argument Example Action
(empty) /catchup Fetch all sources
names /catchup claude,codex Fetch only matching sources
--add /catchup --add "Cursor" https://www.cursor.com/changelog Add a source
--remove /catchup --remove cursor Remove a source
--list /catchup --list Show current sources
--reset /catchup --reset Restore defaults

Workflow

1. Handle Management Commands

If $ARGUMENTS starts with --:

  • Read config-format.md for the workflow of each command
  • Write changes to ~/.catchup/catchup.json
  • Stop — do not fetch changelogs

2. Load Sources

  1. Read ~/.catchup/catchup.json
  2. If missing or invalid, read default-sources.json

3. Apply Filters

If $ARGUMENTS contains comma-separated names (no -- prefix):

  • Split by comma, trim, lowercase each token
  • Keep only sources whose name (lowercased) contains any token
  • If no match, list available source names and stop

4. Fetch Changelogs

For each source:

  1. If the source has a repo field (e.g. "owner/repo"), or the url matches github.com/{owner}/{repo}/releases:
    • Run gh release list --repo {owner/repo} --limit 3 via Bash
    • Then run gh release view {tag} --repo {owner/repo} for each tag to get details
    • If gh succeeds → use this data, skip steps 2–3
  2. Call WebFetch with the source url and this prompt (prepend the source's prompt_hint if present):
    Extract recent changelog/release entries. Return a structured list:
    ### [version or date]
    - Change description
    Keep it concise — maximum 10 bullet points total across all entries.
    If no recent entries are found, say "No recent changes found."
    
  3. If WebFetch fails → try WebSearch with query: "[source name] changelog latest release [current year]"
  4. If all methods fail → record the error, continue to next source

Read the full file on GitHub · 73 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 73 lines · 64 tokens per session scan A 8e5efdba9e7d

Subscribe to this mod's changes

scan is a skill published in the GitHub repository xanoysky/catchup-claude-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 806 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 2026-08-31.