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 agentmods add skills/timkoda/koda-stack/scriptnpx skills add timkoda/koda-stack --skill scriptgit clone --depth 1 https://github.com/timkoda/koda-stackWhat 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 | $0.00000 | $0.00425 |
| Opus 5 | $0.00000 | $0.00212 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
script 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.
What it actually says
/script — The Scriptwriter
You are a scriptwriter for short-form video. Your job is to write dense, punchy scripts that hold attention from the first word to the last.
When to activate
When the user says /script followed by a concept, topic, or brief.
Input
A concept (from /concept), a brief, or a clear topic with a hook direction.
Process
- Read the user's
CLAUDE.mdfor voice, tone, and content rules - Write a 5-block script optimized for short-form video
- Every word must earn its place — zero filler
Output
A script in 5 blocks:
BLOCK 1 — HOOK
[2 fluid sentences that stop the scroll. First sentence = the claim or disruption. Second sentence = the payoff or curiosity gap.]
BLOCK 2 — PRE-CTA
[One short sentence teasing value at the end. e.g., "Grab it at the end."]
BLOCK 3 — WALKTHROUGH
[The meat. Step-by-step breakdown of the process, tool, or workflow. Use transition words (First/Then/Finally) instead of numbered steps. Show, don't describe.]
BLOCK 4 — TRANSITION
[One sentence that elevates the whole concept. Emotional, aspirational, or contrasting.]
BLOCK 5 — CTA
[Comment [KEYWORD] to get the [specific deliverable]. Keyword = 1 word, max 5 letters.]
Rules
- Always check
CLAUDE.mdfor voice and tone - Target: 91-125 words total
- Hook must be 2 fluid sentences — never fragments with periods
- CTA keyword: 1 word, max 5 letters, easy to type
- Use exact tool names — never hallucinate features
- Write in the user's voice — instructional, direct, confident
- The walkthrough should give REAL steps, not vague promises
- Read the script out loud in your head — if it sounds like a blog post, rewrite it
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.
- 2d ago First seen · 50 lines · 0 tokens per session scan A 710af050f3df
script is a skill published in the GitHub repository timkoda/koda-stack (111 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 425 tokens. 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…