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.
npx skills add vnnkl/agentflywheel --skill deep-planninggit clone --depth 1 https://github.com/vnnkl/agentflywheelWrote 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.
[](https://agentmods.dev/skills/vnnkl/agentflywheel/deep-planning)<a href="https://agentmods.dev/skills/vnnkl/agentflywheel/deep-planning"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/deep-planning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vnnkl/agentflywheel/deep-planning"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/deep-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.02266 |
| Opus 5.5 | $0.00029 | $0.00906 |
| Sonnet 5.5 | $0.00014 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
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 2mo 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.
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
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.
- 2mo ago First seen · 245 lines · 72 tokens per session scan A 84f77193bf7e
deep-planning is a skill published in the GitHub repository vnnkl/agentflywheel (2 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 2,266 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…