agentmods.dev

podpull AGENTS.md

A short set of instructions for agents working on podpull, a Python command-line program that downloads podcast episodes from Apple Podcasts, RSS feeds, or Xiaoyuzhou links. It points agents to the repository’s full guide and records important rules for its code and command output.

In plain words
What is it for?
Use it when modifying podpull to understand its architecture, input modes, file naming, text encoding, output streams, and release-related requirements.
Why use it?
It gives coding agents the repository-specific context they need before making changes. This helps preserve behavior such as separating file paths from user-interface messages and avoiding hangs without a terminal.

Instructions file for CodexOpenCode

141 1mo ago A scan 510 tokens original MIT
View the source file xiaoleiy/podpull
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 instructions/xiaoleiy/podpull/agents-md
Clone the repo
git clone --depth 1 https://github.com/xiaoleiy/podpull

Made for: Codex, OpenCode.

Per session 510 This file is loaded in full into every session.
When invoked 510 The same file — it is already loaded in full.
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 $0.00510 $0.00510
Opus 5 $0.00255 $0.00255
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 2d ago against content hash faf100e96efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

podpull AGENTS.md 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 2d 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.

AGENTS.md · 39 lines

What it actually says

AGENTS.md

The full agent guide for this repository is CLAUDE.md — read it first. It covers the architecture, dev workflow, testing, the release process, and the invariants below in detail. This file is a short pointer for agents that look for AGENTS.md.

podpull in one line

A stdlib-core Python CLI that downloads a specific podcast episode's audio from Apple Podcasts, an RSS feed, or a xiaoyuzhou (小宇宙) link. Python ≥ 3.9. Official hosted UI: https://podpull.xiaolei.work (see docs/HOSTING.md).

The must-know invariants (details in CLAUDE.md)

  1. src/podpull/core.py is dependency-free (stdlib only). All third-party deps (rich, questionary, rich-argparse) belong in cli.py. Use callbacks, not imports, to surface UI concerns from core.
  2. stdout = file paths, stderr = all UI. Don't mix them.
  3. podpull get <show> opens the interactive picker only on a TTY without --no-input; otherwise it lists + exits non-zero. Never hang in non-interactive contexts.
  4. Filenames go through core.safe_filename (cloud-/Windows-safe). Text I/O is always encoding="utf-8". core.UA is a browser User-Agent on purpose (xiaoyuzhou 403s tool UAs).
  5. If you change CLI commands/flags, update the bundled agent instructions in src/podpull/integrations/ too.

Quick start

python3 -m venv .venv && . .venv/bin/activate
pip install -e ".[dev]"
pytest -q          # offline; keep green on macOS/Linux/Windows

Releasing

Bump the version in both src/podpull/__init__.py and pyproject.toml, update CHANGELOG.md, then git tag vX.Y.Z && git push origin main --tags — this auto-publishes to PyPI and bumps the Homebrew tap. See CLAUDE.md for the dependency-change caveat.

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. 2d ago First seen · 39 lines · 510 tokens per session scan A faf100e96efe

Subscribe to this mod's changes

podpull AGENTS.md is an instructions file published in the GitHub repository xiaoleiy/podpull (141 stars, last pushed 1mo ago), licensed MIT. It adds 510 tokens to every session, about $0.0026 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.

Git and workflowLanguagesPlanningapple-podcastsclicommand-linem4amp3podcast
Related

Other instructions, from other repositories

ui-ux-pro-max-skill CLAUDE.md

Instructions for nextlevelbuilder/ui-ux-pro-max-skill, covering claude.md, project overview, search command, architecture and sync rules.

nextlevelbuilder/ui-ux-pro-max-skill · 1,386 tokens

tweakcc AGENTS.md

Instructions for Piebald-AI/tweakcc, covering agents.md, development commands, build, testing and linting & formatting.

Piebald-AI/tweakcc · 880 tokens

NeoHaskell AGENTS.md

Instructions for neohaskell/NeoHaskell, covering neohaskell — agent guide, hard rule, style (mandatory), commands (pointers, not a duplicate) and work intake.

neohaskell/NeoHaskell · 3,921 tokens

tokf CLAUDE.md

Instructions for mpecan/tokf, covering tokf — development guidelines, project philosophy, commits, code quality and testing.

mpecan/tokf · 2,341 tokens

vue-tui AGENTS.md

Instructions for vuejs-ai/vue-tui, covering common pitfalls & best practices, project context records (pcr), using vite+, the unified toolchain for the web and review checklist.

vuejs-ai/vue-tui · 3,479 tokens

axe AGENTS.md

Instructions for jrswab/axe, covering axe — agents.md, what this is, design philosophy, non-obvious constraints and what good contributions look like.

jrswab/axe · 3,130 tokens