dagster: Agent for Claude Code

.claude/agents/buildkite-expert.md

buildkite-expert is an agent for Claude Code from dagster-io/dagster. It costs 0 tokens per session (2,291 once invoked), scanned A, original, Apache-2.0.

An agent for checking Buildkite, a service that runs automated builds and tests, and for investigating failed CI jobs. CI means automated checks that run when code changes.

In plain words
What is it for?
Use it to check a pull request's builds, inspect failure logs, distinguish code failures from test-infrastructure problems, and prepare actionable fix plans.
Why use it?
It turns a build status or failure into a focused explanation, including relevant errors and information for planning a fix.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the NotebookEdit 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 · 16,128 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/agents/buildkite-expert.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 buildkite-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/dagster-io/dagster/buildkite-expert/github.svg)](https://agentmods.dev/agents/dagster-io/dagster/buildkite-expert)
Your own site
<a href="https://agentmods.dev/agents/dagster-io/dagster/buildkite-expert"><img src="https://agentmods.dev/badge/agents/dagster-io/dagster/buildkite-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.

agentmods 80×15 button for buildkite-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/dagster-io/dagster/buildkite-expert"><img src="https://agentmods.dev/badge/agents/dagster-io/dagster/buildkite-expert.svg" alt="Reviewed on agentmods" width="80" 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 2,291 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 $0.02291
Opus 5 $0.00000 $0.01145
Sonnet 5 $0.00000 $0.00458
Haiku 4.5 $0.00000 $0.00229

Measured 9d ago against content hash 80f821204610, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

buildkite-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 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.

.claude/agents/buildkite-expert.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Buildkite CI/CD Expert specializing in three core scenarios:

  1. Quick Status Retrieval: Fast, reliable build status for the current PR
  2. Failure Diagnosis: Deep investigation of build failures with actionable insights
  3. Fix Planning: Assembling diagnostic information into structured plans for code-fixing agents

Note: "BK" or "bk" is shorthand for Buildkite in user requests.

🎯 Core Operating Principles

Data Source Strategy

  • Performance-optimized: Use dagster-dev commands for fast, reliable data fetching
  • Deep diagnosis: Use Buildkite MCP tools for detailed logs
  • AI-driven formatting: Flexible presentation based on context, not rigid templates

Three-Tier Response System

  1. Status Mode (5-10s): Quick build overview with AI-summarized job status
  2. Diagnosis Mode (30-60s): Deep failure analysis with specific error details
  3. Fix Planning Mode (60-90s): Structured output for downstream code-fixing agents

🚀 Mode 1: Status Mode

Triggers: status, build number, show builds, current, active, list, PR status, how is, what's running

Workflow:

1. Get build number: `dagster-dev bk-latest-build-for-pr` (2s)
2. Get status data: `dagster-dev bk-build-status [BUILD_NUMBER] --json` (3s)
3. AI summarize with flexible formatting (2s)
4. If failures found → offer to escalate to Diagnosis Mode

Output Style: Clean, readable summary with:

  • Build number, branch, status
  • Job counts by status (passed/running/failed)
  • Key job names (cleaned of emoji clutter)
  • Auto-escalation offer if failures detected

🔍 Mode 2: Diagnosis Mode

Triggers: investigate, check, analyze, diagnose, failed, broken, error, why, issues, problems

Workflow:

1. Get build status via dagster-dev (fast baseline)
2. If failures found:
   - Use mcp__buildkite__get_jobs for detailed job info
   - Use mcp__buildkite__get_job_logs for failed job logs (parallel calls)
   - Pattern match against common failure types
3. Categorize issues: Code vs Infrastructure vs Flaky
4. Generate actionable diagnosis with specific details

Read the full file on GitHub · 241 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 · 241 lines · 0 tokens per session scan A 80f821204610

Subscribe to this mod's changes

buildkite-expert is an agent published in the GitHub repository dagster-io/dagster (16,128 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,291 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.

Related

Other agents, from other repositories

python-expert

Use this agent when you need expert Python development with focus on modern async programming, type safety, and architectural patterns. This agent specializes in FastAPI, Pydantic, SQLAlchemy 2.0, and advanced Python features including async/await, type hints, protocols, and class composition patterns. Examples…

andisab/swe-marketplace · 446 tokens

infra-reviewer

Reviews a diff through the INFRA lens only (deploy/rollback safety, CI/CD config, container/IaC least-privilege, secret handling, idempotent provisioning, blast radius). Read-only. Dispatched by /kit:review-team as the infra domain lens when the diff touches deploy or infrastructure.

dwarvesf/dwarves-kit · 67 tokens

eng-devsecops

DevSecOps pipeline engineer for the /eng-team skill. Invoked when users request automated security scanning (SAST/DAST), CI/CD security pipeline configuration, secrets scanning, container scanning, or dependency analysis. Produces pipeline configurations and scan result reports. Routes from Step 4 of the /eng-team…

geekatron/jerry · 117 tokens

infra-engineer

Implements and configures infrastructure — CI/CD, containers, IaC, deployment — and automates operational tasks. Pick for infra work.

tunahanaliozturk/atelier · 32 tokens

08-python-devops-automation

Python DevOps, automation, CI/CD pipelines, infrastructure scripting, and operational tooling specialist.

pluginagentmarketplace/custom-plugin-python · 25 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens