planning

planning is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 392 tokens per session (3,628 once invoked), scanned A, a copy of planning, MIT.

A method for breaking a complex goal into ordered steps that an agent can execute and adjust as it learns more.

In plain words
What is it for?
Use it to design execution plans, coordinate tools or sub-agents, gather information systematically, and adapt the plan during execution.
Why use it?
It makes multi-step work easier to manage when tasks depend on one another or require several tools and information sources.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to design execution plans, coordinate tools or sub-agents, gather information…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hajekim/agentic-design-patterns-extension/planning
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.

Any agent
npx skills add hajekim/agentic-design-patterns-extension --skill planning
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extension

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 planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/planning.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/planning)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/planning"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/planning.svg" alt="Measured on agentmods" height="20"></a>
Per session 392 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00392 $0.03628
Opus 5 $0.00196 $0.01814
Sonnet 5 $0.00078 $0.00726
Haiku 4.5 $0.00039 $0.00363

Measured 6d ago against content hash 6e32a84c7568, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 6d 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.

Origin

This is a copy

100% identical to planning — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/planning/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planning Pattern

Overview

The Planning Pattern enables an agent to move beyond simple reactive responses by formulating a structured sequence of actions to achieve a complex, high-level goal. Rather than reacting to each input in isolation, a planning agent first analyzes the goal, decomposes it into manageable sub-tasks, and then executes those steps — adapting its plan as new information emerges.

Core Principle: Transform a high-level objective into a structured, executable plan of actionable steps — then adapt the plan as reality unfolds.

When This Skill Applies

Activate this pattern when:

  • A user's request is too complex to handle with a single action or tool call
  • The task requires multiple interdependent steps executed in a logical order
  • The solution path is not known in advance and must be discovered dynamically
  • Workflows involve orchestrating multiple tools, APIs, or sub-agents
  • The agent must adapt its approach based on intermediate results
  • Tasks require systematic information gathering, synthesis, and reporting

Rule of thumb: Use Planning when the "how" needs to be discovered, not just the "what." If the solution requires a sequence of interdependent operations to reach a synthesized outcome — plan first.

DEFINE → PLAN → ACTION Workflow

DEFINE

Understand the planning requirements:

  1. What is the final goal state? What does success look like?
  2. What is the current state, including available resources and constraints?
  3. What sub-tasks are needed to move from initial state to goal state?
  4. What tools, APIs, or agents are available to execute each sub-task?

PLAN

Design the planning architecture:

  1. Map the high-level goal into a directed sequence of executable sub-tasks
  2. Identify dependencies between sub-tasks (which must complete before others begin)
  3. Assign tools, agents, or capabilities to each sub-task
  4. Define checkpoints where the plan can be reassessed based on intermediate results
  5. Plan for contingencies: what if a step fails or returns unexpected results?

Read the full file on GitHub · 366 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. 6d ago First seen · 366 lines · 392 tokens per session scan A 6e32a84c7568

Subscribe to this mod's changes

planning is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 392 tokens to every session and 3,628 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to planning, differing in 3 lines, and is treated as a copy.