plan-next.eval

plan-next.eval is a command for Claude Code from davistroy/claude-marketplace. It costs 0 tokens per session (522 once invoked), scanned A, original, MIT.

A repository-aware planning command that examines a code project’s current files, Git history, status, issues, and existing plans. Git is a tool that records changes to code over time.

In plain words
What is it for?
Use it after recent development work to choose the next coding, testing, documentation, or issue-related action.
Why use it?
It helps decide what to do next using the project’s actual state instead of giving generic advice.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it after recent development work to choose the next coding, testing, documentation, or issue-related action.

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

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.eval

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/plan-next.eval.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/plan-next.eval)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/plan-next.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/plan-next.eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 522 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 $0.00000 $0.00522
Opus 5 $0.00000 $0.00261
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 8d ago against content hash 55fe4ba81f16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

plan-next.eval 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.

evals/commands/plan-next.eval.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval: /plan-next

Purpose

Analyzes the current repository state (git status, recent commits, open issues, existing plans) and recommends the next logical action. Good output: a specific, actionable recommendation grounded in the actual repo state — not a generic "add tests" suggestion.

Fixtures

None — operates on the current repository state.

Test Scenarios

S1: Repo with no open plan

Setup: Ensure no IMPLEMENTATION_PLAN.md exists in the repo root.

Invocation: /plan-next

Must:

  • Reads recent git log, git status, and project structure
  • Produces a recommendation for the next action
  • Recommendation is specific (references actual files, commands, or issues)
  • Provides a rationale for why this is the next action

Should:

  • If recent commits suggest a feature in progress, recommends continuing or testing it
  • If documentation is outdated relative to recent commits, recommends updating it

Must NOT:

  • Recommend an action already reflected in recent commits as "done"
  • Give the same recommendation regardless of repo state (must be context-aware)

S2: Repo with completed IMPLEMENTATION_PLAN.md

Setup: Copy fixtures/plans/implementation-plan.md to repo root and manually set all STATUS markers to done.

Invocation: /plan-next

Must:

  • Detects that the plan is complete
  • Does not recommend implementing an already-complete plan
  • Recommends something appropriate for "plan complete" state (e.g., bump version, clean up, create PR)

S3: Repo with uncommitted changes

Setup: Modify a file and leave it uncommitted.

Invocation: /plan-next

Must:

  • Notes the uncommitted changes in its analysis
  • May recommend committing or completing the in-progress work before starting something new

S4: Read-only behavior

Must:

  • Does not create any files
  • Does not make git commits
  • Analysis is in-conversation only

Rubric

Read the full file on GitHub · 81 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. 8d ago First seen · 81 lines · 0 tokens per session scan A 55fe4ba81f16

Subscribe to this mod's changes

plan-next.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 522 tokens. 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.