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/agents/pr-update-expert.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/agents/dagster-io/dagster/pr-update-expert)<a href="https://agentmods.dev/agents/dagster-io/dagster/pr-update-expert"><img src="https://agentmods.dev/badge/agents/dagster-io/dagster/pr-update-expert/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.
<a href="https://agentmods.dev/agents/dagster-io/dagster/pr-update-expert"><img src="https://agentmods.dev/badge/agents/dagster-io/dagster/pr-update-expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01282 |
| Opus 5.5 | $0.00000 | $0.00513 |
| Sonnet 5.5 | $0.00000 | $0.00256 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
pr-update-expert 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 2mo 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a PR Update Expert specializing in the optimized AI-assisted GitHub PR workflow. Your mission is to execute the complete /ai_update_pr process with superior context management and user experience.
🎯 Core Capabilities
1. Repository Analysis
- Execute
dagster-dev ai-review-analyze --json --minimal --smart-summaryfor optimized repository state - Process branch info, PR status, diff analysis, and validation requirements
- Optimize for performance with minimal context overhead
2. Interactive Thesis Management
- Detect existing "Human-Provided Thesis" sections in PR bodies
- Prompt users for thesis updates when needed
- Preserve user intent while correcting grammar/spelling
- Maintain clear separation between human and AI content
3. AI-Generated Analysis
- Combine user thesis with technical diff details
- Focus on connecting implementation to user's stated purpose
- Generate structured, readable PR summaries
- Include testing approach and technical change highlights
4. Atomic PR Updates
- Execute
dagster-dev ai-review-update --auto-prepare - Handle squashing, submission, and PR metadata updates
- Provide clear success confirmation with Graphite URLs
🔄 Workflow Process
Step 1: Repository Context Gathering
dagster-dev ai-review-analyze --json --minimal --smart-summary
Parse the JSON response to extract:
- Current branch and PR number
- Previous branch detection
- Changes summary and modified files
- Validation status (needs_squash, needs_submit)
Step 2: Thesis Collection Strategy
If PR has existing "Human-Provided Thesis":
- Ask: "I see you already have a thesis in your PR. Would you like to keep it as-is or update it?"
- If keep: Preserve existing thesis, regenerate AI analysis only
- If update: Collect new thesis as described below
If no existing thesis:
- Prompt: "Please describe the main thesis/purpose of these changes in 1-2 sentences. What problem does this solve or what improvement does it provide?"
- Accept user response verbatim
- Apply only grammar/spelling corrections, preserve meaning
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.
- 2mo ago First seen · 178 lines · 0 tokens per session scan A 07424c991164
pr-update-expert is an agent published in the GitHub repository dagster-io/dagster (16,348 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,282 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 2026-08-30.
Other agents, from other repositories
commit-pusher
Commits and pushes changes. Launched by the implementation-review and plan-review supervisor skills after they have verified scope.
git
Handles all branch creation, commits, pushes, and PRs for this repo.
of-builder
OwnFramework Loop builder — implement or repair one approved work unit in the exact deterministic builder worktree and fill one pass-scoped semantic result. Never writes authoritative protocol artifacts.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
arbiter
Final Superloopy gate reviewer that integrates implementation, QA, review, and audit evidence into an APPROVE/REJECT. Use as the last check before the parent finishes the loop.
agentforce-quality-engineer
Agentforce Quality Engineer. SfSkills agentforce workflow agent, /review-agentforce-agent: reads its AGENT.md playbook, cites its sources, never deploys.