aip-tracker

A progress-tracking workflow for Airflow Improvement Proposals, or AIPs—written plans for changes to Apache Airflow. It compares the proposal with evidence from documentation, GitHub changes, and repository files.

In plain words
What is it for?
Use it to assess one or more AIPs, compare specifications with shipped code, and produce an implementation-progress report.
Why use it?
It replaces guesswork with evidence when deciding how much of a planned Airflow change has actually been implemented.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/apache/airflow/aip-tracker
Any agent
npx skills add apache/airflow --skill aip-tracker
Clone the repo
git clone --depth 1 https://github.com/apache/airflow

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,305 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.01305
Opus 5 $0.00020 $0.00652
Sonnet 5 $0.00008 $0.00261
Haiku 4.5 $0.00004 $0.00130

Measured yesterday against content hash 8596094d3990, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aip-tracker 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.

providers/common/ai/src/airflow/providers/common/ai/example_dags/skills/aip-tracker/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIP Progress Tracker Skill

Assess implementation progress of Airflow Improvement Proposals by comparing what the Confluence spec promises against what the codebase delivers.

When to Use This Skill

Use this skill when the task involves:

  • Tracking AIP implementation status
  • Comparing a spec against shipped code
  • Producing a cross-AIP progress report

Available Tools

You have access to these tools for gathering evidence:

  • fetch_confluence_page(page_id) -- fetch an AIP spec from Confluence
  • search_github_prs(query) -- search GitHub PRs/commits for an AIP
  • get_repo_file_tree(path_prefix) -- list files under a directory in the repo

Evidence Gathering Strategy

For each AIP, gather evidence from all three sources before assessing:

  1. Confluence spec -- call fetch_confluence_page with the AIP's page ID. Extract: deliverables, phases, completion criteria, and status.
  2. GitHub PRs and commits -- call search_github_prs with both the AIP number (e.g. "AIP-76") AND topic keywords (e.g. "asset partition"). Deduplicate results.
  3. Codebase file tree -- call get_repo_file_tree with the AIP's known directory prefixes. Count source files and test files.

Deliverable Extraction

Extract deliverables from the specification's own structure. Use these sources in priority order:

  1. Numbered completion criteria (e.g. "Definition of Done", "Completion Criteria") -- each numbered item is one deliverable.
  2. Phase definitions -- each bullet or item under a phase heading is one deliverable.
  3. Explicitly enumerated components (classes, operators, API endpoints, CLI commands, UI features) listed in the spec.

Critical: Do NOT split a single spec item into multiple deliverables (e.g. do not count individual files within one component as separate deliverables). Do NOT merge multiple spec items into one. Use the spec's own granularity -- if the spec says "partition mappers" as one item, that is one deliverable, not five separate file-level deliverables.

Read the full file on GitHub · 144 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. yesterday First seen · 144 lines · 41 tokens per session scan A 8596094d3990

Subscribe to this mod's changes

aip-tracker is a skill published in the GitHub repository apache/airflow (46,647 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 1,305 once invoked, about $0.0002 per session on Opus 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 2026-08-30.