planning

planning is a skill for Claude Code, Codex from huzaifa525/claude-code-optimizer. It costs 32 tokens per session (412 once invoked), scanned A, original, MIT.

A set of instructions for keeping a written plan for complex coding tasks. It uses a file named task_plan.md to record steps, decisions, important files, and blockers.

In plain words
What is it for?
It helps organize tasks involving several steps, files, dependencies, or sessions, and records progress until the plan is removed when the work is complete.
Why use it?
It prevents multi-step work from losing track of what is finished or what should happen next. The plan can also help continue work in a later session.

Skill for Claude CodeCodex

Part of the claude-code-optimizer plugin — 25 skills, 4 hooks shipped together

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.

agentmods
npx agentmods add skills/huzaifa525/claude-code-optimizer/planning
Any agent
npx skills add huzaifa525/claude-code-optimizer --skill planning
Clone the repo
git clone --depth 1 https://github.com/huzaifa525/claude-code-optimizer

Made for: Claude Code, Codex.

Or install claude-code-optimizer, the plugin that ships this one along with the rest of its 25 skills, 4 hooks.

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/huzaifa525/claude-code-optimizer/planning.svg)](https://agentmods.dev/skills/huzaifa525/claude-code-optimizer/planning)
Your own site
<a href="https://agentmods.dev/skills/huzaifa525/claude-code-optimizer/planning"><img src="https://agentmods.dev/badge/skills/huzaifa525/claude-code-optimizer/planning.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00412
Opus 5 $0.00016 $0.00206
Sonnet 5 $0.00006 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 3d ago against content hash c4d808f224c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

templates/.claude/skills/planning/SKILL.md · 60 lines

What it actually says

When working on a complex task, create and maintain a persistent plan in task_plan.md at the project root.

When to Activate

  • Task requires 5+ tool calls or file changes
  • Multiple files need to be created or modified
  • Task has dependencies between steps
  • User explicitly asks to plan

Plan Format

Create task_plan.md with this structure:

# Task: [description]

## Status: In Progress | Completed | Blocked

## Steps

- [x] Step 1: [completed step]
- [ ] Step 2: [current step] ← CURRENT
- [ ] Step 3: [next step]
- [ ] Step 4: [future step]

## Key Files
- [file] → [what needs to change]

## Decisions Made
- [decision and why]

## Blockers
- [any blockers]

Rules

  1. Create plan BEFORE starting work — write task_plan.md first
  2. Update after each step — mark completed, move CURRENT marker
  3. Track decisions — record why you chose an approach
  4. Note blockers — if stuck, write it down
  5. Read plan on resume — if task_plan.md exists, read it first to continue where you left off
  6. Delete on completion — remove task_plan.md when all steps are done

On Session Resume

If task_plan.md exists:

  1. Read it
  2. Find the CURRENT step
  3. Continue from there
  4. Update progress as you go
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. 3d ago First seen · 60 lines · 32 tokens per session scan A c4d808f224c0

Subscribe to this mod's changes

planning is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 412 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 2026-08-31.