deep-planning

deep-planning is a skill for Claude Code, Codex from vnnkl/agentflywheel. It costs 72 tokens per session (2,266 once invoked), scanned A, original, MIT.

A planning workflow that requires a detailed written plan before code is implemented.

In plain words
What is it for?
Use it before building features, starting projects, designing systems, or creating an application when you want the implementation to follow a comprehensive plan.
Why use it?
It moves decisions about architecture, data flow, errors, unusual cases, and security earlier, when they are cheaper to change than working 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/vnnkl/agentflywheel/deep-planning
Any agent
npx skills add vnnkl/agentflywheel --skill deep-planning
Clone the repo
git clone --depth 1 https://github.com/vnnkl/agentflywheel

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for deep-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/vnnkl/agentflywheel/deep-planning.svg)](https://agentmods.dev/skills/vnnkl/agentflywheel/deep-planning)
Your own site
<a href="https://agentmods.dev/skills/vnnkl/agentflywheel/deep-planning"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/deep-planning.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,266 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 $0.00072 $0.02266
Opus 5 $0.00036 $0.01133
Sonnet 5 $0.00014 $0.00453
Haiku 4.5 $0.00007 $0.00227

Measured 4d ago against content hash 84f77193bf7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-planning 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 4d 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/deep-planning/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Planning

Stop. Before writing a single line of code, plan.

This skill enforces a counterintuitive discipline: spend 85% of effort on planning while the entire system still fits in your context window. Once code spreads across hundreds of files, holistic reasoning becomes impossible. A 3,000-line markdown plan is cognitively manageable. The codebase it describes is not.

Why Planning Dominates

There are three reasoning spaces in software development. Each has a radically different cost when mistakes happen:

Space Artifact Rework Cost
Plan Markdown document 1x
Task Bead / work unit 5x
Code Source files 25x

A missed edge case in a plan costs one paragraph to fix. That same edge case discovered during implementation costs refactoring across multiple files, updating tests, fixing cascading type errors, and debugging integration failures. Discovered in production, it costs all of that plus incident response.

Planning tokens are cheap. Implementation tokens are expensive. The rational strategy is to front-load reasoning into the cheapest space.

What Planning Buys You

Global reasoning. During planning, the entire system fits in context. You can reason about how the auth layer interacts with the billing system interacts with the notification pipeline. Once those become 50 separate files, that reasoning is gone.

Security emerges from completeness. You do not need a separate "security phase." A plan detailed enough to describe every data flow, every trust boundary, every user interaction will naturally surface auth gaps, data exposure risks, and injection vectors. Security holes are planning holes.

Mechanical translation. A plan is "done" when converting it to code requires no creative problem-solving — only translation. If an implementer needs to make architectural decisions while coding, the plan failed.

When This Skill Activates

Apply deep planning to any work that involves:

  • Building a new feature with multiple components
  • Starting a new project or application
  • Designing system architecture
  • Implementing workflows that cross multiple boundaries (API, database, UI, external services)
  • Any task where "just start coding" would require backtracking

Read the full file on GitHub · 245 lines

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. 4d ago First seen · 245 lines · 72 tokens per session scan A 84f77193bf7e

Subscribe to this mod's changes

deep-planning is a skill published in the GitHub repository vnnkl/agentflywheel (2 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 2,266 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 2026-08-31.

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