ctx:plan

ctx:plan is a command for coding agents from shakestzd/contextune. It costs 16 tokens per session (3,664 once invoked), scanned A, original, MIT.

A planning command that turns development work into separate YAML task files. YAML is a plain-text format for structured information.

In plain words
What is it for?
Use it to break a project into tasks, mark priorities and dependencies, and prepare work for parallel execution.
Why use it?
It keeps plans smaller and easier to update, reorder, review, and track in version control than one large document.

Command

Part of the contextune plugin — 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server 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 commands/shakestzd/contextune/ctx-plan
Clone the repo
git clone --depth 1 https://github.com/shakestzd/contextune

Or install contextune, the plugin that ships this one along with the rest of its 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server.

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 ctx:plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/shakestzd/contextune/ctx-plan.svg)](https://agentmods.dev/commands/shakestzd/contextune/ctx-plan)
Your own site
<a href="https://agentmods.dev/commands/shakestzd/contextune/ctx-plan"><img src="https://agentmods.dev/badge/commands/shakestzd/contextune/ctx-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,664 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 $0.00016 $0.03664
Opus 5 $0.00008 $0.01832
Sonnet 5 $0.00003 $0.00733
Haiku 4.5 $0.00002 $0.00366

Measured 3d ago against content hash 6d25de35d83e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ctx:plan 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.

commands/ctx-plan.md · 609 lines

How it starts

The opening of the file, as written. The whole thing — 609 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Plan - Create Modular YAML Development Plan

You are executing the parallel planning workflow. Your task is to analyze the conversation history and create a modular YAML plan for parallel development.

Key Innovation: Each task is a separate YAML file. No more monolithic markdown files!

Benefits:

  • ✅ 95% fewer tokens for updates (edit one task file vs entire plan)
  • ✅ Add/remove tasks without touching existing content
  • ✅ Reorder tasks with simple array edits
  • ✅ Better version control (smaller, focused diffs)
  • ✅ No time/duration estimates (use tokens and priority instead)
  • ✅ Priority + dependencies (what actually matters for execution)

DRY Strategy Note:

  • Plans use extraction-optimized output format (visibility + iteration)
  • NO Write tool during planning (user sees full plan in conversation)
  • /ctx:execute extracts plan automatically when needed
  • SessionEnd hook as backup (extracts at session end)
  • Result: Modular files created automatically, zero manual work

This command is part of the Contextune plugin and can be triggered via natural language or explicitly with /contextune:parallel:plan.


Step 1: Analyze Conversation and Requirements

Review the conversation history to identify:

  • What features/tasks the user wants to implement
  • Which tasks are independent (can run in parallel)
  • Which tasks have dependencies (must run sequentially)
  • Potential shared resources or conflict zones

Use the following criteria to classify tasks:

Independent Tasks (Parallel-Safe):

  • Touch different files
  • Different modules/features
  • No shared state
  • Can complete in any order

Dependent Tasks (Sequential):

  • Task B needs Task A's output
  • Database migrations
  • Shared file modifications
  • Order matters

Conflict Risks:

  • Same file edits
  • Shared configuration
  • Database schema changes
  • API contract changes

Step 2: Parallel Research (NEW! - Grounded Research)

IMPORTANT: Before planning, do comprehensive research using 5 parallel agents!

Read the full file on GitHub · 609 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. 3d ago First seen · 609 lines · 16 tokens per session scan A 6d25de35d83e

Subscribe to this mod's changes

ctx:plan is a command published in the GitHub repository shakestzd/contextune (5 stars, last pushed 8mo ago), licensed MIT. It adds 16 tokens to every session and 3,664 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 2026-08-31.