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 agentmods add skills/nicograef/handbook/create-plannpx skills add nicograef/handbook --skill create-plangit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/create-plan)<a href="https://agentmods.dev/skills/nicograef/handbook/create-plan"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/create-plan.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.01416 |
| Opus 5 | $0.00034 | $0.00708 |
| Sonnet 5 | $0.00013 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00142 |
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 yesterday.
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Plan
Create a phased implementation plan from either a PRD or a task
description. Output is a Markdown file in docs/plans/.
Workflow
1. Determine the entry point
- PRD provided (file or in conversation context) → read it fully.
- PRD exists but is not yet in context → ask the user to paste it or point you to the file.
2. Clarify ambiguities
- Always run this step — whether a PRD was provided or not.
- Resolve unknowns through 0–3 rounds of structured questions before planning.
- Follow the canonical clarification question rules.
- Every question clears the ask gate first. Unknowns the codebase, the PRD or the conventions already settle become Resolved decisions, not questions.
- Zero rounds is the correct outcome when nothing survives the gate. Say so in one line and plan.
3. Research the codebase
- Read affected files.
- Understand existing patterns, integration layers, and the current architecture.
4. Identify architectural decisions
Before slicing, identify high-level decisions unlikely to change throughout implementation. They go in the plan header, so every phase can reference them.
- Authentication / authorization approach
- Third-party service boundaries
5. Draft vertical slices
Break the work into tracer bullet phases. Each phase is a thin vertical slice cutting through ALL integration layers end-to-end.
Slice rules:
- Each slice delivers a narrow but COMPLETE path through every layer (schema, API, UI, tests).
- A completed slice is demoable or verifiable on its own.
- Prefer many thin slices over few thick ones.
- Do NOT include specific file names, function names, or implementation details likely to change as later phases are built.
- DO include durable decisions: route paths, schema shapes, data model names.
- Give every phase a
**Depends on**line — the phase numbers that must land first, or "none". - implement-plan reads that line to decide what may run concurrently.
- A plan without that line is executed strictly sequentially.
- Every phase is then assumed to depend on all earlier ones.
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.
- yesterday Changed · -14 lines 65f597819e72
- 5d ago First seen · 193 lines · 67 tokens per session scan A 547a1dceafa2
create-plan is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,416 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…