plan-next

plan-next is a command for Claude Code from davistroy/claude-marketplace. It costs 8 tokens per session (2,671 once invoked), scanned A, original, MIT.

A repository-analysis command that examines the current project state and recommends one highest-priority next action. It checks planning files, Git status, and available project content.

In plain words
What is it for?
Use it in a Git repository to identify the next pending plan item or other logical action based on the repository's current state.
Why use it?
It helps choose what to do next when a repository has several possible tasks or an existing implementation plan. It also reports when the project is empty or cannot be analyzed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Use it in a Git repository to identify the next pending plan item or other logical action based on the repository's current state.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/davistroy/claude-marketplace/plan-next
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.

Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 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 plan-next

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/plan-next/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/plan-next)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/plan-next"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/plan-next/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for plan-next

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/plan-next"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/plan-next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,671 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 $0.00008 $0.02671
Opus 5 $0.00004 $0.01336
Sonnet 5 $0.00002 $0.00534
Haiku 4.5 $0.00001 $0.00267

Measured 9d ago against content hash 890a6eb79455, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plan-next 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 9d 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.

plugins/personal-plugin/commands/plan-next.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Next Step Analysis

Analyze the current state of this repository and recommend the single highest-priority next action. This command is plan-aware, git-aware, and produces structured output with clear rationale.

Input Validation

No Arguments Required: This command takes no arguments.

If extra arguments are provided, they are ignored.

Before proceeding, verify:

  • This is a valid git repository (.git/ directory exists)
  • Key project files are accessible (at minimum, one of: README.md, CLAUDE.md, or source files)
  • The repository has meaningful content (not an empty init)

If the repository is empty or inaccessible, stop and report:

Error: Cannot analyze repository

The repository appears to be empty or inaccessible. Ensure you are in the
root of a git repository with at least some committed content.

Instructions

Analysis Process

Execute the following steps in order. Each step feeds into the decision logic below.

Step 1: Check for Active Plans

Search for planning artifacts in the repository root:

  1. IMPLEMENTATION_PLAN.md — Read it if found. Identify:
    • Total phases and which phase is current
    • The next PENDING work item (by phase order)
    • Any IN_PROGRESS items (these take priority — they represent interrupted work)
    • Overall completion percentage (count COMPLETE vs total items)
  2. RECOMMENDATIONS.md — Read it if found. Note:
    • Whether recommendations exist that have no corresponding implementation plan
    • Any items marked as Critical priority
  3. PROGRESS.md or TODO.md — Read if found. Note any tracked items.
  4. Open GitHub Issues — Run gh issue list --limit 10 --state open (if gh is available). Note count and any high-priority labels.

Record what was found and what was not.

Step 2: Check Git State

Run these commands and record the results:

  1. git status --short — Check for uncommitted changes (staged, unstaged, untracked)
  2. git branch --show-current — Get current branch name
  3. git log --oneline -5 — Get recent commit messages for context
  4. git stash list — Check for stashed changes
  5. gh pr list --author @me --state open --limit 5 — Check for open PRs (if gh available)

Read the full file on GitHub · 266 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. 9d ago First seen · 266 lines · 8 tokens per session scan A 890a6eb79455

Subscribe to this mod's changes

plan-next is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 2,671 once invoked, about $0.0000 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.