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 hajekim/agentic-design-patterns-extension --skill planninggit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extensionWrote 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/hajekim/agentic-design-patterns-extension/planning)<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>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 | $0.00392 | $0.03628 |
| Opus 5 | $0.00196 | $0.01814 |
| Sonnet 5 | $0.00078 | $0.00726 |
| Haiku 4.5 | $0.00039 | $0.00363 |
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.
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.
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:
- What is the final goal state? What does success look like?
- What is the current state, including available resources and constraints?
- What sub-tasks are needed to move from initial state to goal state?
- What tools, APIs, or agents are available to execute each sub-task?
PLAN
Design the planning architecture:
- Map the high-level goal into a directed sequence of executable sub-tasks
- Identify dependencies between sub-tasks (which must complete before others begin)
- Assign tools, agents, or capabilities to each sub-task
- Define checkpoints where the plan can be reassessed based on intermediate results
- Plan for contingencies: what if a step fails or returns unexpected results?
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.
- 6d ago First seen · 366 lines · 392 tokens per session scan A 6e32a84c7568
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.
Other skills, from other repositories
prompt engineering
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workflow.
redteam
Expertise in offensive security research, vulnerability analysis, CMS-focused application testing, and red team operations.
redteam-source-audit
Focused source-code security review workflow for web applications, CMS extensions, APIs, and supporting services.
redteam-cms
Focused methodology for authorized CMS fingerprinting, component inventory, misconfiguration review, and vulnerability validation.
redteam-exploit-validation
Focused workflow for validating exploitability safely and turning candidate issues into reproducible, bounded proof.
redteam-recon
Focused reconnaissance workflow for authorized security assessments, bug bounty triage, lab targets, and CTF infrastructure.