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.
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.
curl -O https://raw.githubusercontent.com/dagster-io/dagster/master/.claude/commands/erk/replan.mdgit clone --depth 1 https://github.com/dagster-io/dagsterWrote 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.
[](https://agentmods.dev/commands/dagster-io/dagster/replan)<a href="https://agentmods.dev/commands/dagster-io/dagster/replan"><img src="https://agentmods.dev/badge/commands/dagster-io/dagster/replan.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.01485 |
| Opus 5 | $0.00006 | $0.00743 |
| Sonnet 5 | $0.00002 | $0.00297 |
| Haiku 4.5 | $0.00001 | $0.00148 |
Grade A, and why
replan 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/erk:replan
Recomputes an existing erk-plan issue against the current codebase state, creating a new plan and closing the original.
Usage
/erk:replan 2521
/erk:replan https://github.com/owner/repo/issues/2521
Agent Instructions
Step 1: Parse Issue Reference
Extract the issue number from the argument:
- If numeric (e.g.,
2521), use directly - If URL (e.g.,
https://github.com/owner/repo/issues/2521), extract the number from the path
If no argument provided, ask the user for the issue number.
Step 2: Fetch Original Issue
erk exec get-issue-body <number>
This returns JSON with {success, issue_number, title, body, state, labels, url}. Store the issue title and check that:
- Issue exists
- Issue has
erk-planlabel
If not an erk-plan issue, display error:
Error: Issue #<number> is not an erk-plan issue (missing erk-plan label).
If issue is already closed, display warning but continue:
Warning: Issue #<number> is already closed. Proceeding with replan anyway.
Step 3: Fetch Plan Content
The plan content is stored in the first comment's plan-body metadata block:
gh issue view <number> --comments --json comments
Parse the first comment to find <!-- erk:metadata-block:plan-body --> section.
Extract the plan content from within the <details> block.
If no plan-body found, display error:
Error: No plan content found in issue #<number>. Expected plan-body metadata block in first comment.
Step 4: Deep Investigation
Use the Explore agent (Task tool with subagent_type=Explore) to perform deep investigation of the codebase. This is the most important step - surface-level analysis leads to poor plans.
4a: Check Plan Items Against Codebase
For each implementation item in the plan:
- Search for relevant files, functions, or patterns
- Determine status: implemented, partially implemented, not implemented, or obsolete
Build a comparison table showing:
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.
- 7d ago First seen · 229 lines · 12 tokens per session scan A 174f52efc5cb
replan is a command published in the GitHub repository dagster-io/dagster (16,114 stars, last pushed 2d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,485 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.