airflow-hitl

airflow-hitl is a skill for Claude Code from astronomer/agents. It costs 126 tokens per session (1,764 once invoked), scanned A, original, Apache-2.0.

Airflow operators for human-in-the-loop workflows, where an automated data workflow pauses for a person's response. Airflow is a system for scheduling and running workflows, and a DAG is one such workflow definition.

In plain words
What is it for?
Use them for approval or rejection gates, selecting options, branching on a human decision, collecting form data, or building custom human-response steps in Airflow 3.1 or newer.
Why use it?
They let a workflow wait for approval, a choice, or form input without occupying a worker while it waits. The person's response can also determine which later tasks run.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the astronomer-data plugin — 35 skills, 3 commands shipped together

Good fit Use them for approval or rejection gates, selecting options, branching on a human decision, collecting form data, or building custom human-response steps in Airflow 3.1 or newer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/astronomer/agents/airflow-hitl
Install

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.

Any agent
npx skills add astronomer/agents --skill airflow-hitl
Clone the repo
git clone --depth 1 https://github.com/astronomer/agents

Made for: Claude Code.

Or install astronomer-data, the plugin that ships this one along with the rest of its 35 skills, 3 commands.

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 airflow-hitl

README.md
[![agentmods](https://agentmods.dev/badge/skills/astronomer/agents/airflow-hitl/github.svg)](https://agentmods.dev/skills/astronomer/agents/airflow-hitl)
Your own site
<a href="https://agentmods.dev/skills/astronomer/agents/airflow-hitl"><img src="https://agentmods.dev/badge/skills/astronomer/agents/airflow-hitl/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 airflow-hitl

Your own site · 80×15
<a href="https://agentmods.dev/skills/astronomer/agents/airflow-hitl"><img src="https://agentmods.dev/badge/skills/astronomer/agents/airflow-hitl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,764 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 30 Apr 2026
  • Snyk pass 30 Apr 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00126 $0.01764
Opus 5 $0.00063 $0.00882
Sonnet 5 $0.00025 $0.00353
Haiku 4.5 $0.00013 $0.00176

Measured 9d ago against content hash 20c80dac6e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

airflow-hitl scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

requests.get(f"{HOST}/<path>", headers=HEADERS, params={"state": "pending"})
skills/airflow-hitl/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Airflow Human-in-the-Loop Operators

Pause a DAG until a human responds via the Airflow UI or REST API. HITL operators are deferrable — they release their worker slot while waiting.

Requires Airflow 3.1+ (af config version).

UI location: Browse → Required Actions. Respond from the task instance page's Required Actions tab.

Cross-references: migrating-ai-sdk-to-common-ai for AI/LLM task decorators; airflow for registry and API discovery commands used below.


Step 1 — Pick the capability you need

Capability Class (verify in Step 2)
Approve or reject; downstream skips on reject ApprovalOperator
Present N options and return which were chosen HITLOperator
Branch to one or more downstream tasks based on a choice HITLBranchOperator
Collect a form (no approve/select step) HITLEntryOperator
Use the HITL trigger directly (advanced / custom operators) HITLTrigger

This is the only place class names are hardcoded. The provider adds, renames, and removes params across releases — do not copy parameter lists from memory. Fetch the current signature before writing code.


Step 2 — Discover the current signatures from the Airflow Registry

Before writing HITL code, run these to see the live roster and constructor params (see the airflow skill for the full af registry reference):

# Every HITL-related module in the standard provider
af registry modules standard \
  | jq '.modules[] | select(.import_path | test("\\.hitl\\.")) | {name, type, import_path, short_description, docs_url}'

# Constructor signatures: name, type, default, required, description
af registry parameters standard \
  | jq '.classes | to_entries[] | select(.key | test("\\.hitl\\.")) | {fqn: .key, parameters: .value.parameters}'

# Pin to the exact installed provider version
af config providers \
  | jq '.providers[] | select(.package_name == "apache-airflow-providers-standard") | .version'
# then: af registry parameters standard --version <VERSION>

Read the full file on GitHub · 185 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 · 185 lines · 126 tokens per session scan A 20c80dac6e26

Subscribe to this mod's changes

airflow-hitl is a skill published in the GitHub repository astronomer/agents (439 stars, last pushed 3d ago), licensed Apache-2.0. It adds 126 tokens to every session and 1,764 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

workers-best-practices

Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.

cloudflare/skills · 25 tokens

notion_synthesize

Synthesize durable ktx wiki pages and semantic-layer sources from staged Notion pages, databases, data-source rows, and clustered Notion evidence. Load when a WorkUnit contains Notion raw files or Notion evidence chunks.

Kaelio/ktx · 50 tokens

historic_sql_table_digest

Convert one changed historic-SQL table usage bucket into typed table usage evidence for deterministic schema projection.

Kaelio/ktx · 25 tokens

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

elvisun/newsjack · 69 tokens

story-origin-check

Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

elvisun/newsjack · 40 tokens

relevance-coarse-filter

Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.

elvisun/newsjack · 57 tokens