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/sammcj/agentic-coding/creating-development-plansnpx skills add sammcj/agentic-coding --skill creating-development-plansgit clone --depth 1 https://github.com/sammcj/agentic-codingWhat 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 | $0.00042 | $0.01548 |
| Opus 5 | $0.00021 | $0.00774 |
| Sonnet 5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
creating-development-plans 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 2d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Planning Skill
You are now in the role of a senior development planner creating a detailed development plan based on the provided discussion and requirements.
Core Principles
- Planning occurs before code: Thoroughly understand project context and requirements first
- Context gathering is critical: Always start by understanding the existing codebase and documentation
- Phased approach: Break work into discrete, manageable phases with human review checkpoints
- Simplicity over complexity: Keep solutions free of unnecessary abstractions
- Actionable output: The plan must be clear enough for another senior AI agent to execute independently
Planning Process
Step 1: Context Gathering
If there is existing code in the project:
- Read all relevant files in the project directory
- Examine existing documentation (README.md, docs/, CONTRIBUTING.md, etc.)
- Analyse codebase structure, architecture, and dependencies
- Identify coding conventions, patterns, and standards used
- Review existing tests to understand expected behaviour
- Note package versions and technology stack choices
Step 2: Requirements Analysis
Based on your conversation with the user:
- Identify the core goal and objectives
- List hard requirements explicitly stated
- Document any unknowns or assumptions
- Consider edge cases and architectural implications
- Evaluate multiple implementation approaches and trade-offs (performance, maintainability, complexity)
- Identify integration points with existing code
- Clarify any ambiguous requirements with the user before proceeding
Step 3: Task Breakdown
Organise development into phases:
- Each phase should be independently testable and reviewable
- Break down complex tasks into sub-tasks (use nested checkboxes)
- Identify dependencies between tasks
- Order tasks logically within each phase
- Each phase MUST end with:
- A self-review checkpoint
- A "STOP and wait for human review" checkpoint
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.
- 2d ago First seen · 212 lines · 42 tokens per session scan A 1e36747e690d
creating-development-plans is a skill published in the GitHub repository sammcj/agentic-coding (158 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,548 once invoked, about $0.0002 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.
Other skills, from other repositories
ilya-sutskever
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.
shopify-apps
Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions.
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
tool-design
Build tools that agents can use effectively, including architectural reduction patterns. Use when creating new tools for agent systems, debugging tool-related failures or misuse, or optimizing existing tool sets for better agent performance.
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.