planning

planning is a skill for Claude Code, Codex from byronxlg/skillfold. It costs 14 tokens per session (324 once invoked), scanned A, original, MIT.

A planning guide for breaking a goal into smaller steps, showing what each step produces, what depends on it, and how to check it.

In plain words
What is it for?
Use it to plan coding tasks, projects, investigations, or other work that has several dependent parts.
Why use it?
It reduces confusion about where to start and makes unknowns, risks, effort, and parallel work visible before implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan coding tasks, projects, investigations, or other work that has several dependent parts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/byronxlg/skillfold/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 byronxlg/skillfold --skill planning
Clone the repo
git clone --depth 1 https://github.com/byronxlg/skillfold

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/byronxlg/skillfold/planning.svg)](https://agentmods.dev/skills/byronxlg/skillfold/planning)
Your own site
<a href="https://agentmods.dev/skills/byronxlg/skillfold/planning"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/planning.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 324 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 original No closer match found 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 $0.00014 $0.00324
Opus 5 $0.00007 $0.00162
Sonnet 5 $0.00003 $0.00065
Haiku 4.5 $0.00001 $0.00032

Measured 8d ago against content hash 68c7e1548bfe, 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 8d 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.

library/skills/planning/SKILL.md · 39 lines

What it actually says

Planning

You break problems into concrete, actionable steps. Your plans are structured, dependency-aware, and scoped to the information available.

Principles

  • Start from the desired outcome and work backward to identify what must happen
  • Every step should have a clear deliverable and a way to verify completion
  • Identify dependencies between steps - what blocks what
  • Separate what you know from what you need to find out
  • Prefer smaller steps that can be validated independently over large leaps

Approach

When building a plan:

  1. Clarify the goal. Restate it in concrete, measurable terms
  2. Identify the major phases or milestones between now and the goal
  3. Break each phase into discrete steps with inputs, outputs, and acceptance criteria
  4. Map dependencies - which steps require outputs from other steps
  5. Flag unknowns and risks. For each, note what information would resolve it
  6. Estimate relative effort (small, medium, large) based on complexity and uncertainty
  7. Identify which steps can run in parallel

Scope Estimation

  • Account for verification and testing time, not just implementation
  • Unknowns increase scope - flag them explicitly rather than hiding them in estimates
  • If a step seems too large to estimate, break it down further

Output

Produce a numbered plan with steps grouped by phase. Each step includes: what to do, what it depends on, what it produces, and how to verify it is done. Flag parallel opportunities and open questions.

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. 8d ago First seen · 39 lines · 14 tokens per session scan A 68c7e1548bfe

Subscribe to this mod's changes

planning is a skill published in the GitHub repository byronxlg/skillfold (12 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 324 once invoked, about $0.0001 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.