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.
npx agentmods add commands/dagster-io/dagster/enforce_standardsgit clone --depth 1 https://github.com/dagster-io/dagsterWhat 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 | $0.00000 | $0.00538 |
| Opus 5 | $0.00000 | $0.00269 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
enforce_standards 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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enforce Standards Command
Step 0: Stack Preparation with Merge Conflict Detection
CRITICAL: Before running the code standards enforcer, we must prepare the stack properly and abort if there are merge conflicts.
Sequential commands (must be run in order):
gt squash- Squash commits in the current branch for cleaner historygt restack- Ensure the stack is properly synced and up-to-date
Important: These commands must be run sequentially, not in parallel. If either command fails due to merge conflicts, abort the entire operation and inform the user that merge conflicts must be resolved manually before running standards enforcement.
Merge Conflict Detection:
- If
gt squashfails with merge conflicts, abort and tell user to resolve conflicts first - If
gt restackfails with merge conflicts, abort and tell user to resolve conflicts first - Only proceed to standards enforcement if both commands succeed without conflicts
Step 1: Invoke Code Standards Enforcer Agent
After successful stack preparation, use the Task tool to launch the code-standards-enforcer agent with the following configuration:
Agent Type: code-standards-enforcer
Task Description: "Audit changed files for standards compliance"
Detailed Prompt:
Please perform a comprehensive audit of all changed files in the current PR against the coding standards defined in CLAUDE.md.
Focus on:
1. Files that have been modified in the current branch compared to the base branch
2. Compliance with coding conventions from .claude/coding_conventions.md
3. Adherence to development workflow requirements from .claude/dev_workflow.md
4. Proper use of type annotations and @record decorators
5. Code quality requirements including mandatory `just ruff` execution
After the audit, provide:
- A summary of any standards violations found
- Specific recommendations for fixes
- List of files that need attention
- Confirmation that mandatory code quality checks (just ruff) have been run
If no violations are found, confirm that all changed files comply with the project's coding standards.
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.
- yesterday First seen · 66 lines · 0 tokens per session scan A 44b18df188f3
enforce_standards is a command published in the GitHub repository dagster-io/dagster (16,073 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 538 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 commands, from other repositories
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.
add-task-module
Scaffold a new task module (classification/regression/clustering/...).
work-on-approved-issue
Pick an Approved GitHub issue and resolve it end-to-end.
run-engine-tests
Fast local test loop for the engine package.
cron
Schedule skills to run automatically at specific times or based on events.