cold-open-creator

A guide for writing 25–35-second podcast openings that begin inside a tense story rather than summarizing the episode. It uses story beats such as a goal, disruption, failed attempt, and new insight.

In plain words
What is it for?
Use it to find a complete story arc in an episode, select its strongest tension point, and write a cold open that leads into the rest of the conversation.
Why use it?
It helps an episode start with an unresolved moment that creates curiosity, instead of giving listeners a plain introduction or trailer.

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/cdeistopened/skill-stack/cold-open-creator
Any agent
npx skills add cdeistopened/skill-stack --skill cold-open-creator
Clone the repo
git clone --depth 1 https://github.com/cdeistopened/skill-stack

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,646 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 $0.00052 $0.03646
Opus 5 $0.00026 $0.01823
Sonnet 5 $0.00010 $0.00729
Haiku 4.5 $0.00005 $0.00365

Measured 2d ago against content hash 02e5aed19f75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cold-open-creator 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.

.claude/skills/cold-open-creator/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Podcast Cold Open Creator

Purpose

Create 25-35 second cold opens that drop listeners into a story arc - someone who wanted something, encountered obstacles, and figured something out. The cold open cuts at the tension peak, before the resolution.

Core Philosophy: The cold open is not a summary or a trailer. It's a story interrupted at the moment of maximum tension. They should finish the cold open asking "How did we get here?" and "What happens next?"


The Narrative Snippets Method (Primary Approach)

The best cold opens follow recognizable story beats. Instead of searching for "good moments," search for complete story arcs, then cut them at the right point.

The Story Beats

Every compelling story follows this pattern:

Beat What Happens Cold Open Role
1. Setup Protagonist in their world, pursuing something INCLUDE - establishes context
2. Disaster Something disrupts the status quo INCLUDE - creates tension
3. Failed Approach They try the obvious solution, it backfires INCLUDE - shows stakes
4. New Insight A realization that changes everything TEASE or CUT HERE
5. Resolution They apply the insight, it works CUT BEFORE THIS
6. Reflection The universal takeaway CUT BEFORE THIS

The Rule: Include beats 1-3 (maybe hint at 4). Cut BEFORE beats 5-6. The cold open ends with the question unresolved.

Finding Story Arcs in Transcripts

Scan for these signal phrases:

Disaster signals:

  • "Then everything fell apart..."
  • "I was diagnosed with..."
  • "The call came and they said no..."
  • "I realized I was doing it wrong..."

Failed approach signals:

  • "I tried X but it didn't work..."
  • "We did everything we were supposed to..."
  • "Most people just accept it and move on..."

Insight signals (CUT HERE OR JUST BEFORE):

  • "Then I realized..."
  • "That's when it clicked..."
  • "So what we do instead is..." [CUT]
  • "The real reason was..." [CUT]

Read the full file on GitHub · 419 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 419 lines · 52 tokens per session scan A 02e5aed19f75

Subscribe to this mod's changes

cold-open-creator is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 3,646 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 2026-08-30.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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