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/ooiyeefei/ccc/pitch-decknpx skills add ooiyeefei/ccc --skill pitch-deckgit clone --depth 1 https://github.com/ooiyeefei/cccWrote 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/ooiyeefei/ccc/pitch-deck)<a href="https://agentmods.dev/skills/ooiyeefei/ccc/pitch-deck"><img src="https://agentmods.dev/badge/skills/ooiyeefei/ccc/pitch-deck.svg" alt="Measured on agentmods" 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 | $0.00136 | $0.00821 |
| Opus 5 | $0.00068 | $0.00411 |
| Sonnet 5 | $0.00027 | $0.00164 |
| Haiku 4.5 | $0.00014 | $0.00082 |
Grade A, and why
pitch-deck 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 6d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch Deck - one HTML file, narrated, recordable
The deck is the backdrop; the speech carries the pitch. So the deck's job is: one idea per slide, minimal text, numbers that are cited or cut, and navigation reliable enough to drive by hand on stage or by script on camera. One file, no CDN - it must open from disk, on a venue machine, with no network.
Steps
1. Outline: one slide, one idea
Derive the slide list from the pitch story (the pitch-craft skill's storytelling rules apply to structure too). A proven arc to adapt, not worship:
Hook -> what-it-is 101 -> the cost of the status quo -> Reveal (name + throughline) -> test bed / credibility -> the concrete example -> how it works (one flow, end to end) -> "watch it work" (the demo slot) -> the differentiator ("it learns") -> one-more-thing -> roadmap -> architecture -> Close (numbers land again + name).
Appendix slides (anticipated hard questions: safety, "is this really agentic", adoption, commercials) go AFTER the close, are never narrated, and are opened only when a judge asks.
2. Build the single file
Follow references/deck-patterns.md: section-per-slide skeleton, hash-based deep links (#11 starts at slide 11 - the recorder depends on this), data-anim staggered entries, a fixed brand mark in the top-right of every slide, progress bar + counter. Rules that earn their keep: cited or cut (every industry number hyperlinks a real source, verified to load), vector icons never emojis, synthetic-data disclaimers as one corner legend rather than per-slide clutter.
3. Narrate via pitch-craft
Hand the slide list to the pitch-craft skill for the walkthrough script (per-slide timestamp windows, recorded register). If the deck will also be presented live, have pitch-craft write the LIVE variant separately (team intro after the hook, stage cues, trim points) - the two registers do not interchange.
4. Record the walkthrough (optional)
Follow references/deck-recording.md: per-slide HOLD durations derived from the narration windows, recorded in two parts around the demo slot (Part A ends paused on the demo slide, Part B fresh-loads after it). The recording harness lives in the demo-video skill (demo-video/scripts/record_template.py) - single source of truth; this skill only contributes the deck-specific driver (click #next, hold per window).
What ships with it
3 files 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.
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.
- 6d ago First seen · 40 lines · 136 tokens per session scan A d0ec2d97c468
pitch-deck is a skill published in the GitHub repository ooiyeefei/ccc (484 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 821 once invoked, about $0.0007 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.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…