MCPInstall

plan

Lightweight planning with optional interview

Installs
119
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/yeachan-heo/oh-my-codex --skill plan
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads plan automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

<Purpose> Plan creates concise, actionable work plans. Auto-detects interview vs direct, supports `--interview` for Socratic clarification and `--review` for evaluation. </Purpose>

<Use_When>

  • Planning before implementation — "plan this", "let's plan"
  • Requirements are vague and need scoping — use --interview
  • Reviewing an existing plan — --review </Use_When>

<Do_Not_Use_When>

  • Want direct execution — execute the scoped task directly; use ultragoal only for durable goals or team for coordinated parallel work
  • Simple focused fix with obvious scope — skip planning </Do_Not_Use_When>

<Execution_Policy>

  • Auto-detect interview vs direct; --interview forces Socratic mode, --direct skips it
  • Ask one question at a time; gather codebase facts first
  • omx explore is deprecated. Use normal repository inspection for codebase facts; omx sparkshell only for explicit shell-native evidence
  • Plans must be evidence-backed: 80%+ claims cite file/line, 90%+ criteria testable
  • Right-size steps to scope; save to .omx/plans/ </Execution_Policy>
<Steps>

Mode Selection

ModeTriggerBehavior
Interview--interview or broad requestSocratic requirements gathering
Direct--direct or detailed requestGenerate plan immediately
Review--reviewCritic evaluation of existing plan

Interview (--interview)

  1. Classify request; ask one focused question via omx question
  2. Gather codebase facts first, then ask informed follow-ups
  3. Build on answers; consult Analyst for hidden requirements
  4. Create plan when user signals readiness

Direct

  1. Quick analysis (optional Analyst)
  2. Generate plan immediately
  3. Optional Critic review if requested

Review (--review)

  1. Read plan from .omx/plans/
  2. Evaluate via Critic; verdict APPROVED/REVISE/REJECT
  3. If author == reviewer, hand off to $code-review

Output

Every plan includes: Requirements Summary, Acceptance Criteria (testable), Implementation Steps (with file refs, adaptive count), Risks/Mitigations, Verification. Saved to .omx/plans/.

Outcome-first framing: apply outcome-first framing, concise visible updates for multi-step planning. Local overrides for the active workflow branch apply via newer user task updates. If the user says continue, continue the current branch instead of restarting.

</Steps>

<Tool_Usage>

  • omx explore is deprecated. Use normal repository inspection; omx sparkshell only for explicit shell-native evidence
  • Use omx question for interview questions; plain text only as fallback
  • Use ask_codex with planner/analyst/critic as needed </Tool_Usage>

<Escalation_And_Stop_Conditions>

  • Stop interviewing when requirements are clear — do not over-interview
  • Escalate on irreconcilable trade-offs requiring business decision
  • "just do it" / "skip planning" → hand off to $ultragoal </Escalation_And_Stop_Conditions>

<Final_Checklist>

  • Acceptance criteria testable (90%+ concrete)
  • Claims cite file/line (80%+)
  • Risks have mitigations, no vague terms
  • Plan saved to .omx/plans/ </Final_Checklist>
<Advanced> ## Question Classification | Type | Examples | Action | |------|----------|--------| | Codebase Fact | "Where is X?" | Explore first, do not ask | | User Preference | "Priority?" | Ask via `omx question` | | Scope Decision | "Include Y?" | Ask user |

Review Quality Criteria

CriterionStandard
Clarity80%+ claims cite file/line
Testability90%+ criteria concrete
VerificationFile refs exist
</Advanced>

FAQ

What does the plan skill do?

Lightweight planning with optional interview

How do I install plan?

Run npx skills add https://github.com/yeachan-heo/oh-my-codex --skill plan in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/plan/ (personal) or .claude/skills/plan/ (project).

Which AI agents can use plan?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is plan safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains plan?

It is published by yeachan-heo in yeachan-heo/oh-my-codex. It has 119 recorded installs.

More from yeachan-heo/oh-my-codex

View all →

deep-interview

yeachan-heo/oh-my-codex

Socratic deep interview with mathematical ambiguity gating before execution

196 installs

ultraqa

yeachan-heo/oh-my-codex

Adversarial dynamic e2e QA workflow - generate hostile scenarios, test, verify, fix, report, and clean up

Testing & QA166 installs

ralplan

yeachan-heo/oh-my-codex

Consensus planning stage for Planner - Architect - Critic handoff to $ultragoal

ralph

yeachan-heo/oh-my-codex

Sunset stub — use $ultragoal instead

159 installs

ai-slop-cleaner

yeachan-heo/oh-my-codex

Run an anti-slop cleanup/refactor/deslop workflow

team

yeachan-heo/oh-my-codex

N coordinated agents on shared task list using tmux-based orchestration

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.