airflow-hitl

airflow-hitl is a skill for Claude Code, Codex from miptah21/skills. It costs 71 tokens per session (2,029 once invoked), scanned C, original, MIT.

A set of Apache Airflow operators that pause a workflow until a person approves, rejects, fills in a form, or chooses a path. Airflow is a tool for scheduling and running data workflows.

In plain words
What is it for?
Use it for approval gates, form-based input, and human-selected branching in Airflow DAGs. It requires Airflow 3.1 or newer.
Why use it?
It adds human decisions to automated workflows without custom polling code. It also lets waiting tasks release their worker slot.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it for approval gates, form-based input, and human-selected branching in Airflow DAGs. It requires Airflow 3.1 or newer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/miptah21/skills/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 miptah21/skills --skill airflow-hitl
Clone the repo
git clone --depth 1 https://github.com/miptah21/skills

Made for: Claude Code, Codex.

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/miptah21/skills/airflow-hitl.svg)](https://agentmods.dev/skills/miptah21/skills/airflow-hitl)
Your own site
<a href="https://agentmods.dev/skills/miptah21/skills/airflow-hitl"><img src="https://agentmods.dev/badge/skills/miptah21/skills/airflow-hitl.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00071 $0.02029
Opus 5 $0.00036 $0.01014
Sonnet 5 $0.00014 $0.00406
Haiku 4.5 $0.00007 $0.00203

Measured 8d ago against content hash 5fd352956615, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

airflow-hitl scanned grade C with 2 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 8d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- lint-ignore-file-size -->

Makes network callslowCapability

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

r = requests.get(f"{HOST}/api/v2/hitlDetails/?state=pending",
.agents/skills/airflow-hitl/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Airflow Human-in-the-Loop Operators

Implement human approval gates, form inputs, and human-driven branching in Airflow DAGs using the HITL operators. These deferrable operators pause workflow execution until a human responds via the Airflow UI or REST API.

Implementation Checklist

Execute steps in order. Prefer deferrable HITL operators over custom sensors/polling loops.

CRITICAL: Requires Airflow 3.1+. NOT available in Airflow 2.x.

Deferrable: All HITL operators are deferrable—they release their worker slot while waiting for human input.

UI Location: View pending actions at Browse → Required Actions in Airflow UI. Respond via the task instance page's Required Actions tab or the REST API.

Cross-reference: For AI/LLM calls, see the airflow-ai skill.


Step 1: Choose operator

Operator Human action Outcome
ApprovalOperator Approve or Reject Reject causes downstream tasks to be skipped (approval task itself succeeds)
HITLOperator Select option(s) + form Returns selections
HITLBranchOperator Select downstream task(s) Runs selected, skips others
HITLEntryOperator Submit form Returns form data

Step 2: Implement operator

ApprovalOperator

from airflow.providers.standard.operators.hitl import ApprovalOperator
from airflow.sdk import dag, task, chain, Param
from pendulum import datetime

@dag(start_date=datetime(2025, 1, 1), schedule="@daily")
def approval_example():
    @task
    def prepare():
        return "Review quarterly report"

    approval = ApprovalOperator(
        task_id="approve_report",
        subject="Report Approval",
        body="{{ ti.xcom_pull(task_ids='prepare') }}",
        defaults="Approve",  # Optional: auto on timeout
        params={"comments": Param("", type="string")},
    )

    @task
    def after_approval(result):
        print(f"Decision: {result['chosen_options']}")

    chain(prepare(), approval)
    after_approval(approval.output)

approval_example()

Read the full file on GitHub · 298 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. 8d ago First seen · 298 lines · 71 tokens per session scan C 5fd352956615

Subscribe to this mod's changes

airflow-hitl is a skill published in the GitHub repository miptah21/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 2,029 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens