Apache Airflow is a platform for defining, scheduling, and monitoring workflows as code, with a scheduler assigning dependent tasks to workers. Teams use it to orchestrate automated data and software pipelines and inspect their progress through a user interface. Its catalogue skills and instructions help agents work with Airflow.
Borrowing it
Nothing to install: this file belongs to apache/airflow. 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/apache/airflow/main/.agents/skills/airflow-pr-draft-summary/SKILL.mdgit clone --depth 1 https://github.com/apache/airflowWrote 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/skills/apache/airflow/airflow-pr-draft-summary)<a href="https://agentmods.dev/skills/apache/airflow/airflow-pr-draft-summary"><img src="https://agentmods.dev/badge/skills/apache/airflow/airflow-pr-draft-summary/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/skills/apache/airflow/airflow-pr-draft-summary"><img src="https://agentmods.dev/badge/skills/apache/airflow/airflow-pr-draft-summary.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 | $0.00037 | $0.01342 |
| Opus 5.5 | $0.00015 | $0.00537 |
| Sonnet 5.5 | $0.00007 | $0.00268 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
airflow-pr-draft-summary 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 19d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Airflow contribution text
Use the sections below for the requested contribution text. For PR descriptions,
follow the repository template, keep
titles under 70 characters, and complete the Gen-AI checkbox and Generated-by:
attribution when applicable. Report only checks actually executed and their outcomes.
For release-note decisions, also follow the newsfragment constraints in root
AGENTS.md.
When deciding whether an issue is needed or preparing authorized publication, use Publish Airflow changes. Return the requested text for a drafting request; drafting alone does not authorize posting.
Commit messages, PR titles and release notes
Write commit messages focused on user impact, not implementation details.
- Good:
Fix airflow dags test command failure without serialized Dags - Good:
UI: Fix Grid view not refreshing after task actions - Good:
Update foo function - Bad:
Initialize Dag bundles in CLI get_dag function - Bad:
Update foo function (#12345) - Bad:
fix(cli): dags test failure— Airflow does not use Conventional Commits (feat:,fix:,chore:…). Write the subject as plain prose. Acommit-msgprek hook (check-no-conventional-commit-message) rejects these, and CI checks every commit of the PR.
Always run prek install before committing any code. It installs the
commit-msg hook (in addition to pre-commit) so the Conventional Commits guard
runs locally; a clone that ran prek install before this hook existed must re-run
it to pick up the new hook type.
Use the imperative mood and a plain message — do not use Conventional Commits prefixes
(fix:, feat:, chore:, docs:, refactor:, …). apache/airflow does not follow that
convention. (Area tags the project already uses, like UI: / API: / Helm:, are fine;
Conventional-Commit type: tokens are not.) The same rule applies to PR titles.
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.
- 19d ago Changed · -2 lines 69ba204f4fae
- 1mo ago First seen · 120 lines · 37 tokens per session scan A d8e1cacf3269
airflow-pr-draft-summary is a skill published in the GitHub repository apache/airflow (47,377 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,342 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-18.
airflow-pr-draft-summary compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| airflow-pr-draft-summaryapache/airflow | Skill | 47k | yesterday | Apache-2.0 | A | 37 | Claude Code, Codex |
| git-workflowvstorm-co/pydantic-deepagents | Skill | 1.1k | 7d ago | MIT | A | 17 | Claude Code, Codex |
| development-workflowathola/claude-night-market | Skill | 348 | yesterday | MIT | A | 20 | Claude Code |
| git-flow-prsoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 103 | Claude Code, Codex |
| repository-manager-bulk-git-operationsKnuckles-Team/repository-manager | Skill | 3 | yesterday | MIT | A | 140 | Claude Code, Codex |
| git-workflowchandrudp29/skillhub | Skill | 14 | 4mo ago | MIT | A | 41 | Claude Code, Codex |
| antigravity-maintainer-batch-releaseranbot-ai/awesome-skills | Skill | 8 | yesterday | none | A | 50 | Claude Code, Codex |