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)
- Current focus — what file/task is actively being worked on right now
- Most recent concrete change — what just got written, edited, run, or decided
- Blocker or open question — anything waiting on the user, or that's stuck
- Next step — the very next action the agent intends to take, if obvious
- Notable side effects — files created, branches touched, processes started, only if relevant
What to leave out
- Restating the original user request verbatim
- Tool-call narration ("I ran ls, then grep, then…")
- Anything that happened more than ~10 turns ago unless it's still load-bearing
- Hedging, qualifiers, or meta-commentary about the summary itself
Example
User: /cmd-what
Good response:
- **Editing**: refactoring `auth/session.py` to drop the legacy cookie path
- **Tests**: 14/16 passing, 2 failing on token refresh edge case
- **Blocked**: need to know if expired refresh tokens should silently re-auth or 401
- **Next**: wire the chosen behavior into `refresh_token()` once you decide
Bad response (too verbose, narrates tool calls, future-tense, missing labels):
- I started by reading the auth module and then I grepped for cookie usage
- I'm planning to refactor the session handling but first I want to check with you
- The tests will probably need updates too
1---2name: cmd-code-what3description: 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.4---56# What <!-- omit in toc -->78Give 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.910## Output format1112Reply with **3-5 bullet points only**. No preamble, no closing summary, no headers, no follow-up questions. Each bullet must be:1314```15- **1-3 word label**: explanation in less than 120 characters16```1718Hard rules:1920- **3-5 bullets, no more, no less in spirit** (4 is the sweet spot)21- **Label**: 1-3 words, bolded, title-case or kebab-case, names a concrete thing (file, action, decision, blocker)22- **Explanation**: a single clause, **< 120 characters including the label**, present tense or past tense — never future tense ("will", "going to")23- No nested bullets, no code fences, no links, no emoji unless one is genuinely load-bearing24- 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 terminal2526## What to include (in priority order)27281. **Current focus** — what file/task is actively being worked on right now292. **Most recent concrete change** — what just got written, edited, run, or decided303. **Blocker or open question** — anything waiting on the user, or that's stuck314. **Next step** — the very next action the agent intends to take, if obvious325. **Notable side effects** — files created, branches touched, processes started, only if relevant3334## What to leave out3536- Restating the original user request verbatim37- Tool-call narration ("I ran ls, then grep, then…")38- Anything that happened more than ~10 turns ago unless it's still load-bearing39- Hedging, qualifiers, or meta-commentary about the summary itself4041## Example4243User: `/cmd-what`4445Good response:4647```48- **Editing**: refactoring `auth/session.py` to drop the legacy cookie path49- **Tests**: 14/16 passing, 2 failing on token refresh edge case50- **Blocked**: need to know if expired refresh tokens should silently re-auth or 40151- **Next**: wire the chosen behavior into `refresh_token()` once you decide52```5354Bad response (too verbose, narrates tool calls, future-tense, missing labels):5556```57- I started by reading the auth module and then I grepped for cookie usage58- I'm planning to refactor the session handling but first I want to check with you59- The tests will probably need updates too60```
olshansk