agent-doc-discipline
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and…
Summarize authored commits over a period, grouped by theme with commit-range evidence, mechanical churn separated, and unfinished branches named. For standups and 'what did I get done'.
Claude Code
$ npx -y skills add Yeachan-Heo/oh-my-claudecode --skill what-did-i-get-done --agent claude-code
Codex
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill what-did-i-get-done -a codex -y
Cursor
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill what-did-i-get-done -a cursor -y
Gemini CLI
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill what-did-i-get-done -a gemini-cli -y
GitHub Copilot
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill what-did-i-get-done -a github-copilot -y
OpenCode
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill what-did-i-get-done -a opencode -y
Windsurf
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill what-did-i-get-done -a windsurf -y
name: what-did-i-get-done
description: "Summarize authored commits over a period, grouped by theme with commit-range evidence, mechanical churn separated, and unfinished branches named. For standups and 'what did I get done'."
aliases: []
metadata:
credits:
authored-work-summary: pstack
author: Lauren Tan
url: "https://github.com/cursor/plugins/tree/main/pstack"
port: pstack-claude
port-author: Michael Denyer
port-url: "https://github.com/michael-denyer/pstack-claude"Summarize authored work from the record, not from memory.
1. **Establish identity and window**: which author(s) and what period (default: the last 7 days; take the user's override). 2. **Collect**: `git log --author=<you> --since=<window> --stat` across the repos in play; include merged PRs via `gh pr list --author <you> --state merged --search "merged:>=<window-start>" --limit 500` where the user cares about review surface (`--state` defaults to `open`, so it must be named; `--author` needs its value; the default limit of 30 silently truncates a busy window — pass an explicit limit or paginate until a page comes back short). 3. **Group by theme**, not by commit: a theme line names the outcome ("auth retry hardening"), the commits underneath are the evidence. 4. **Count honestly**: commits, net lines, tests added. Mechanical churn (renames, lockfiles) is grouped separately or left out, never passed off as progress. 5. **Started-but-unfinished**: branches and PRs opened but not landed in the window, each with what remains — the section standups actually need.
For Codex users: Check out oh-my-codex — the same orchestration experience for OpenAI Codex CLI. Liked OmC but found it a bit overkill? Try gajae-code.
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and…
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Settle types and module shape before cross-boundary code — competing designs explored in parallel, compared on API surface and…
Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical…
Run N parallel candidates at one brief and synthesize: rubric-first framing, isolated fan-out, a cross-judge on a different…
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration