/create-a-big-plan
Create a large Prime Agent plan before implementation. Use for open-ended or high-risk repo efforts needing 10 or more planning questions, web research, reviewer or criticizer subagents, and refinement until convergence; exclude direct implementation-only, factual/explanation,
$ npx -y skills add Optim-Agent/optim-plans --skill create-a-big-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/create-a-big-plan
Context preview
The summary Claude sees to decide when to auto-load this skill.
Create a large Prime Agent plan before implementation. Use for open-ended or high-risk repo efforts needing 10 or more planning questions, web research, reviewer or criticizer subagents, and refinement until convergence; exclude direct implementation-only, factual/explanation,
SKILL.md
create-a-big-plan.SKILL.mdname: create-a-big-plan
description: Create a large Prime Agent plan before implementation. Use for open-ended or high-risk repo efforts needing 10 or more planning questions, web research, reviewer or criticizer subagents, and refinement until convergence; exclude direct implementation-only, factual/explanation, trivial command-only, or explicit no-plan requests.
Create A Big Plan
Use this skill when the user wants a large, high-risk, or open-ended plan before a repository change.
Setup
1. Read `../_shared/references/prime-planning-workflow.md`, `../_shared/references/state-and-config.md`, and `../_shared/references/plan-artifact-template.md`. 2. Initialize state with `python3 scripts/optim_plans.py init --repo <target-repo> --topic <topic> --plan-level create-a-big-plan --request-text <original-request>`. 3. Use `.git/optim-plans` for controller state and `docs/optim-plans/YYYY-MM-DD-topic/` for public artifacts.
Depth Contract
- Inspect the target Git repo read-only before the first product question.
- Ask at least 10 planning questions, one at a time. There is no maximum; stop only when the decision tree is resolved.
- Use web research during both brainstorming and refinement when outside facts, patterns, or ecosystem constraints matter.
- Use the standard choice prompt format: recommended first, `Other` second-last, `Auto-complete` last.
- Ask the mandatory final scope confirmation before writing `PLAN_v1.md`.
- Write `PLAN_v1.md` under `docs/optim-plans/YYYY-MM-DD-topic/`.
- Run reviewer or criticizer refinement until convergence while high-priority findings, unresolved criticizer questions, or evidence gaps remain.
- In each refinement round, surface at most five high-priority comments or questions.
- After convergence or user acceptance, ask the native execution handoff question without `Auto-complete`.
Fit
Choose this level for new systems, large feature surfaces, cross-repository work, open-ended architecture, safety-sensitive changes, unclear workflows, or plans where the shape is not yet known.
Use `reference-before-plan` instead when downloaded external projects, papers, articles, or documentation must be studied before planning choices are safe.
Read more
name: create-a-big-plan description: Create a large Prime Agent plan before implementation. Use for open-ended or high-risk repo efforts needing 10 or more planning questions, web research, reviewer or criticizer subagents, and refinement until convergence; exclude direct implementation-only, factual/explanation, trivial command-only, or explicit no-plan requests.
Create A Big Plan
Use this skill when the user wants a large, high-risk, or open-ended plan before a repository change.
Setup
1. Read `../_shared/references/prime-planning-workflow.md`, `../_shared/references/state-and-config.md`, and `../_shared/references/plan-artifact-template.md`. 2. Initialize state with `python3 scripts/optim_plans.py init --repo <target-repo> --topic <topic> --plan-level create-a-big-plan --request-text <original-request>`. 3. Use `.git/optim-plans` for controller state and `docs/optim-plans/YYYY-MM-DD-topic/` for public artifacts.
Depth Contract
- Inspect the target Git repo read-only before the first product question.
- Ask at least 10 planning questions, one at a time. There is no maximum; stop only when the decision tree is resolved.
- Use web research during both brainstorming and refinement when outside facts, patterns, or ecosystem constraints matter.
- Use the standard choice prompt format: recommended first, `Other` second-last, `Auto-complete` last.
- Ask the mandatory final scope confirmation before writing `PLAN_v1.md`.
- Write `PLAN_v1.md` under `docs/optim-plans/YYYY-MM-DD-topic/`.
- Run reviewer or criticizer refinement until convergence while high-priority findings, unresolved criticizer questions, or evidence gaps remain.
- In each refinement round, surface at most five high-priority comments or questions.
- After convergence or user acceptance, ask the native execution handoff question without `Auto-complete`.
Fit
Choose this level for new systems, large feature surfaces, cross-repository work, open-ended architecture, safety-sensitive changes, unclear workflows, or plans where the shape is not yet known.
Use `reference-before-plan` instead when downloaded external projects, papers, articles, or documentation must be studied before planning choices are safe.
Human-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer agent workflows.
Other skills on optim-plans.
- /create-a-plan
Create a researched Prime Agent plan before implementation. Use for broad or risky repo changes needing 5 to 10 planning questions, web research, reviewer or criticizer settings, and bounded refinement; exclude direct implementation-only, factual/explanation, trivial
Open skill - /create-a-small-plan
Create a small Prime Agent plan before implementation. Use for small scoped repo changes needing 1 to 3 planning questions and one reviewer or criticizer refinement pass; exclude direct implementation-only, factual/explanation, trivial command-only, or explicit no-plan requests.
Open skill - /diagnose-before-plan
Diagnose failures before creating a Prime Agent plan. MUST USE for bugs, CI failures, test failures, regressions, incidents, broken behavior, root cause, RCA, or debug-why requests before deciding whether to plan; preserve language, reviewer, and criticizer settings in
Open skill - /reference-before-plan
Research references before creating a Prime Agent plan. Use when repo-change planning needs downloaded projects, articles, papers, docs, per-reference analysis, adoption questions, language settings, and reviewer or criticizer subagents; exclude direct implementation-only,
Open skill