dagster: Command for Claude Code

.claude/commands/erk/objective-next-plan.md

objective-next-plan is a command for Claude Code from dagster-io/dagster. It costs 8 tokens per session (2,034 once invoked), scanned A, original, Apache-2.0.

A command that creates an implementation plan for one step of a project objective tracked in a GitHub issue. An implementation plan breaks a larger goal into concrete coding work.

In plain words
What is it for?
Use it to start planning a specific objective step before making code changes.
Why use it?
It turns a broad objective into a focused next piece of work. It can use an issue number, issue URL, or a previously assigned objective from a work slot.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

This is dagster-io/dagster's own configuration. It tells Claude Code how to work on dagster itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dagster configures →

About the project

Dagster is a platform for developing, running, and observing data assets, such as datasets and the processes that produce them. It is used to organize and automate data workflows.

dagster-io/dagster · 16,114 stars · on GitHub · dagster.io

Reuse

Borrowing it

Nothing to install: this file belongs to dagster-io/dagster. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dagster-io/dagster/master/.claude/commands/erk/objective-next-plan.md
Clone the repo
git clone --depth 1 https://github.com/dagster-io/dagster

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 objective-next-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/dagster-io/dagster/objective-next-plan.svg)](https://agentmods.dev/commands/dagster-io/dagster/objective-next-plan)
Your own site
<a href="https://agentmods.dev/commands/dagster-io/dagster/objective-next-plan"><img src="https://agentmods.dev/badge/commands/dagster-io/dagster/objective-next-plan.svg" alt="Measured on agentmods" 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 2,034 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 $0.02034
Opus 5 $0.00004 $0.01017
Sonnet 5 $0.00002 $0.00407
Haiku 4.5 $0.00001 $0.00203

Measured 7d ago against content hash 51258c2655b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

objective-next-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 7d 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.

.claude/commands/erk/objective-next-plan.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/erk:objective-create-plan

Create an implementation plan for a specific step in an objective's roadmap.

Usage

/erk:objective-create-plan 3679
/erk:objective-create-plan https://github.com/owner/repo/issues/3679
/erk:objective-create-plan  # prompts for issue reference

Agent Instructions

Step 1: Parse Issue Reference

Parse $ARGUMENTS to extract the issue reference:

  • If argument is a URL: extract issue number from path
  • If argument is a number: use directly
  • If no argument provided: try to get the default from pool.json (see below), then prompt if no default

Getting default objective from pool.json:

If no argument is provided, check if we're in a pool slot worktree with a last objective:

erk exec slot-objective

This returns JSON like:

{ "objective_issue": 123, "slot_name": "erk-slot-01" }

Or if not in a slot or no objective:

{ "objective_issue": null, "slot_name": null }

If objective_issue is not null, use it as the default and inform the user: "Using objective # from slot's last objective. Run with explicit argument to override."

If no default found or not in a pool slot, prompt user using AskUserQuestion with "What objective issue should I work from?"

Step 2: Fetch and Validate Issue

erk exec get-issue-body <issue-number>

This returns JSON with {success, issue_number, title, body, labels, url}.

Validate this is an objective:

  1. Check for erk-objective label in the labels array
  2. If label is erk-plan instead: report error "This is an erk-plan issue, not an objective. Use /erk:plan-implement instead."
  3. If neither label: warn but proceed

Step 2.5: Create Objective Context Marker

Create a marker to persist the objective issue number for the exit-plan-mode hook.

erk exec marker create --session-id "${CLAUDE_SESSION_ID}" \
  --associated-objective <objective-number> objective-context

Replace <objective-number> with the issue number from Step 2.

Read the full file on GitHub · 253 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. 7d ago First seen · 253 lines · 8 tokens per session scan A 51258c2655b3

Subscribe to this mod's changes

objective-next-plan is a command published in the GitHub repository dagster-io/dagster (16,114 stars, last pushed 2d ago), licensed Apache-2.0. It adds 8 tokens to every session and 2,034 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 2026-08-30.