Cmd Code What

Catch the user up on what the agent has been doing in the current session with 3-5 ultra-tight bullet points. Use when the user invokes /cmd-what, asks "what are you doing", "what did you do", "catch me up", "status", "where are we", or otherwise needs a fast situational summary of in-flight agent work.

9 starsSoftware Development Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add Olshansk/agent-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Olshansk/agent-skills --skill cmd-code-what
Manual install
git clone --depth 1 https://github.com/Olshansk/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/cmd-code-what ~/.claude/skills/cmd-code-what

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# What 

Give the user a high-signal, low-noise snapshot of what's happened in this session so they can re-enter the loop without scrolling back.

## Output format

Reply with **3-5 bullet points only**. No preamble, no closing summary, no headers, no follow-up questions. Each bullet must be:

```
- **1-3 word label**: explanation in less than 120 characters
```

Hard rules:

- **3-5 bullets, no more, no less in spirit** (4 is the sweet spot)
- **Label**: 1-3 words, bolded, title-case or kebab-case, names a concrete thing (file, action, decision, blocker)
- **Explanation**: a single clause, **< 120 characters including the label**, present tense or past tense — never future tense ("will", "going to")
- No nested bullets, no code fences, no links, no emoji unless one is genuinely load-bearing
- Skip anything the user already knows from the last 1-2 turns — focus on what they'd miss if they just walked back to the terminal

## What to include (in priority order)

1. **Current focus** — what file/task is actively being worked on right now
2. **Most recent concrete change** — what just got written, edited, run, or decided
3. **Blocker or open question** — anything waiting on the user, or that's stuck
4. **Next step** — the very next action the agent intends to take, if obvious
5. **Notable side effects** — files created, branches touched, processes started, only if relevant

## What to leave out

- Restating the original user request verbatim
Read the full skill on GitHub

Details

Skill name
cmd-code-what
Path
skills/cmd-code-what/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Cmd Code What skill do?

Catch the user up on what the agent has been doing in the current session with 3-5 ultra-tight bullet points. Use when the user invokes /cmd-what, asks "what are you doing", "what did you do", "catch me up", "status", "where are we", or otherwise needs a fast situational summary of in-flight agent work.

How do I install the Cmd Code What skill?

Claude Code plugin: /plugin marketplace add Olshansk/agent-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cmd Code What popular?

It lives in Olshansk/agent-skills, which has 9 GitHub stars and 0 forks.

Related skills

Cmd Agent Persona Set

9

Olshansk/agent-skills

Prime the agent with a behavioral persona for the conversation

AI, LLMs & Agents

Cmd Clean Code

9

Olshansk/agent-skills

Improve code readability without altering functionality using idiomatic best practices

Software Development

Cmd Codex Review Plan

9

Olshansk/agent-skills

Get a second opinion on the current plan from Codex (codex exec headless mode) before leaving plan mode. Pipes the plan to codex, captures critique and gap analysis, then proposes a revised plan with an explicit changelog of what changed and what was rejected. Triggers on "/cmd-codex-review-plan", "review plan with codex", "ask codex about this plan", or before approving auto mode on an exit-plan prompt.

Software Development

Cmd Codex Review Unstaged

9

Olshansk/agent-skills

Get a second opinion on what Claude just implemented from Codex (codex exec headless mode). Pipes Claude's summary plus the working-tree diff to codex, asks codex to leverage cmd-pr-follow-up and cmd-pr-edgecase methodology to surface bugs, test gaps, edge cases, and simplification opportunities, then synthesizes a prioritized iteration plan from the feedback. Triggers on "/cmd-codex-review-unstaged", "review my changes with codex", "have codex review what I just did", or after a non-trivial implementation pass before commit.

Software Development

Auto Scope

9

borkweb/skills

Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.

Software Development

Cmd Makefile

9

Olshansk/agent-skills

Create or improve Makefiles with minimal complexity. Templates available: base, python-uv, python-fastapi, postgres, nodejs, go, chrome-extension, flutter, electron, static-site.

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.