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.
npx skills add Squared-Lemons-Ltd/podmule-plugin --skill find-in-back-cataloguegit clone --depth 1 https://github.com/Squared-Lemons-Ltd/podmule-pluginWrote 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/squared-lemons-ltd/podmule-plugin/find-in-back-catalogue)<a href="https://agentmods.dev/skills/squared-lemons-ltd/podmule-plugin/find-in-back-catalogue"><img src="https://agentmods.dev/badge/skills/squared-lemons-ltd/podmule-plugin/find-in-back-catalogue/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/squared-lemons-ltd/podmule-plugin/find-in-back-catalogue"><img src="https://agentmods.dev/badge/skills/squared-lemons-ltd/podmule-plugin/find-in-back-catalogue.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 | $0.00058 | $0.00930 |
| Opus 5 | $0.00029 | $0.00465 |
| Sonnet 5 | $0.00012 | $0.00186 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
find-in-back-catalogue 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 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find it in the back catalogue
A podcast back catalogue is the one thing a general-purpose model cannot know. Everything here is read-only, so it is safe to run before any conversation about permissions.
PodMule holds two different views of the same recordings, and picking the wrong one is the main way this goes wrong.
Transcripts are the evidence layer
search_transcripts searches the actual words people said, as spoken. Reach for it when the answer has to be defensible:
- a verbatim quote, or the passage around one
- an exact timestamp — "where does she say that?"
- "which episodes discuss X" / "episodes about X"
Its matched_episodes field is the episode list. It is already deduplicated per episode, so it is the right thing to read back to someone asking "which episodes"; re-deriving that list from the individual chunk hits produces duplicates and a worse ordering.
A single chunk is usually too small to quote from — it starts and ends mid-thought. get_transcript_window expands a hit into the surrounding section with start and end timestamps, which is what an answer of the form "at 14:32 he says …" actually needs.
Not every hit is timestamped. A result with a null start_time_seconds matched the episode's written description rather than the recording, and no amount of expanding will give it a position in the audio. Treat those as "this episode is about that", not as a quote — asserting a timestamp that was never in the result is the one way to make this layer untrustworthy.
Knowledge is the synthesis layer
search_knowledge searches durable pages PodMule maintains per show: one page per episode, plus topic pages and guest pages that accumulate across the whole catalogue. Reach for it when the question is about the show's position rather than a moment in it:
- "what does the show think about X"
- a topic overview, or how a theme developed over time
- everything a recurring guest has contributed
- takeaways across the back catalogue
Results come back mixed: page_type: "topic" pages span the catalogue, page_type: "episode" pages cover one recording, and guest pages cover one person. For "what does the show think about X", the topic page is the answer and the episode pages are supporting detail — a topic page's summary names how many episodes it draws on, which is the fastest read on whether a theme is a recurring position or a one-off.
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.
- 9d ago First seen · 54 lines · 58 tokens per session scan A e8730b9d5cbd
find-in-back-catalogue is a skill published in the GitHub repository Squared-Lemons-Ltd/podmule-plugin (0 stars, last pushed 21d ago), licensed MIT. It adds 58 tokens to every session and 930 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
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…