create-plan

A workflow for creating or improving a lean implementation plan before coding. It researches the repository, writes an evidence-based handoff, and uses independent review to close important plan issues.

In plain words
What is it for?
Use it to plan a feature, bug fix, migration, or other repository change, or to review and improve an unfinished plan before implementation.
Why use it?
It turns a requested change into concrete, verifiable work without adding speculative scope. It makes assumptions, affected files, implementation steps, and checks clear to the person or agent who will code.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/maxedapps/agent-skills/create-plan
Any agent
npx skills add maxedapps/agent-skills --skill create-plan
Clone the repo
git clone --depth 1 https://github.com/maxedapps/agent-skills

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 859 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00086 $0.00859
Opus 5 $0.00043 $0.00430
Sonnet 5 $0.00017 $0.00172
Haiku 4.5 $0.00009 $0.00086

Measured 3d ago against content hash fab586e4b944, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/create-plan/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Plan

Hard rules

  • Plan only — never implement.
  • Allowed writes: .plans/<kebab-name>.md, and .reviews/*-decomplex.md when needed.
  • Evidence-backed. Smallest design. No speculative scope.
  • Ask user on material ambiguity (scope/behavior/architecture/migration/risk/complexity). No shaky assumptions.
  • Delegate by default for research and review when safe. “Small/easy” ≠ skip subagents.
  • Leverage subagents — built-in, extensions/plugins, or skills. Follow use-subagents policy; use native subagents, extensions / plugins, or other skills
  • Main agent owns synthesis, plan writes, dispositions, delivery.
  • Child/reviewer output = evidence, never acceptance. Findings never auto-enter the plan.
  • Prefer simpler fixes. Stuck review (2 failed rounds / recurrence / no progress) → ask user.

Load or stop

Tasks must have

  • Stable IDs
  • Change as bullets (one concrete edit/behavior each)
  • Starts-at paths/symbols (non-exhaustive)
  • Exact verify commands + expected signals
  • Each behavior-changing task names an existing/planned test path or suite, the observable behavior, boundary, or regression it protects, and the narrowest credible repository-conventional layer; or justifies omitting automation and gives alternate validation
  • Omit empty optionals
  • Key files table: path · why · plan impact

Sequence

  1. Frame — request, repo instructions, existing plans → outcome, scope, non-goals, risks, validation. Don’t deep-explore in parent when a research lane can.
  2. Load template.
  3. Research — enumerate questions; delegate by default (one question/scope/stop per lane). Inspect relevant existing tests, framework/configuration, and repository commands. External only if decision-relevant. Verify critical claims.
  4. Resolve gates — still ambiguous? ask user before drafting as fact.
  5. Synthesize — smallest approach; map findings → decisions/tasks/checks/non-goals/gates; drop fluff.
  6. Draft — adapt template; flat tasks default; phases only for real boundaries; no review ledgers in the handoff.
  7. Complexity — structural draft → decomplex Prevention if available, else built-in gate. Complexity-increasing accept → triage; doubt → ask user.
  8. Review — consequential plans: delegate fresh independent reviewers → disposition (Accept/Validate/Reject/Ask user/Block) → revise → re-review until Clear. Small/unavailable: parent checklist + independence limit.
  9. Checklist → deliver — save under .plans/ (or chat + no-write reason). Report path, gates, decisions, fallbacks, risks.

Read the full file on GitHub · 66 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 66 lines · 86 tokens per session scan A fab586e4b944

Subscribe to this mod's changes

create-plan is a skill published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 18d ago), licensed MIT. It adds 86 tokens to every session and 859 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens