agent-doc-discipline
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and…
Play back the goal, the problem, and the success check in your own words when a brief is genuinely ambiguous — vague, contested, or leaving real forks open — so misunderstanding is caught cheaply. Not for well-specified or routine tasks.
Claude Code
$ npx -y skills add Yeachan-Heo/oh-my-claudecode --skill in-your-own-words --agent claude-code
Codex
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill in-your-own-words -a codex -y
Cursor
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill in-your-own-words -a cursor -y
Gemini CLI
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill in-your-own-words -a gemini-cli -y
GitHub Copilot
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill in-your-own-words -a github-copilot -y
OpenCode
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill in-your-own-words -a opencode -y
Windsurf
$ npx skills add Yeachan-Heo/oh-my-claudecode --skill in-your-own-words -a windsurf -y
name: in-your-own-words
description: "Play back the goal, the problem, and the success check in your own words when a brief is genuinely ambiguous — vague, contested, or leaving real forks open — so misunderstanding is caught cheaply. Not for well-specified or routine tasks."
aliases: []
metadata:
credits:
goal-playback: 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"Before the first tool call on genuinely ambiguous work — a brief that is vague, contested, or leaves real forks open — say back what you understood — in your words, not the user's phrasing echoed. Misunderstanding caught now costs a sentence; caught after execution it costs the work. A well-specified brief needs no playback: start, and report what you did.
Three parts, plain language:
1. **The goal**: what the user will have when this is done. 2. **The problem** (if any): what stands in the way, as you understand it. 3. **The success check**: how we will know it worked.
Then one line: "Right? Correct me where I drifted." — and stop for the answer on risky work; proceed-and-report on clearly reversible work (`principles` skill, Never block on the human).
you have not understood it yet.
it, do not smooth it.
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