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 commands/dkorobtsov/pitch-deck/creategit clone --depth 1 https://github.com/dkorobtsov/pitch-deckWhat 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 | $0.00042 | $0.06747 |
| Opus 5 | $0.00021 | $0.03374 |
| Sonnet 5 | $0.00008 | $0.01349 |
| Haiku 4.5 | $0.00004 | $0.00675 |
Grade A, and why
create 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.
How it starts
The opening of the file, as written. The whole thing — 848 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch Deck Builder
Build investor-grade pitch decks through narrative-first methodology. Story before slides. Writing before design. Meaning before data.
Core principle: Audiences skim. Decision-makers use heuristics. If you give them too much info and not enough meaning, they make sub-optimal decisions. Your job: engineer the takeaways.
Execution Phases
This skill runs in sequential phases. Complete each phase before moving to the next. Get user approval at each gate.
Phase 0: Founder Interview
Before anything else, understand the founder and the business through a structured interview.
Check for existing interview: If ./pitch/pitch-interview.md exists, ask the user:
"I found a previous interview at ./pitch/pitch-interview.md. Would you like to use it, or start fresh?"
If starting fresh (or no previous interview exists), ask these 12 questions ONE AT A TIME. Wait for each answer before asking the next. Follow up on interesting answers — dig deeper when you sense passion, unique insight, or a story worth telling.
- What does your company do? Explain it like I'm 5
- What specific pain does your product solve? Who feels this pain most acutely?
- Why did YOU start this company? What's your personal connection to the problem?
- What's your unfair advantage — why can YOUR team win this?
- What traction do you have? Users, revenue, LOIs, growth rate — anything earned, not just done
- Who are your competitors? Be honest — what do they do better, and where do you win?
- What's your business model? How do you make money, and what are the unit economics?
- What's the market size? (Think bottom-up: how many potential customers × what they'd pay)
- What's your biggest risk right now? What keeps you up at night?
- How much are you raising, and what will you do with the money? What milestones will it unlock?
- What's the 3-year vision? What does the world look like if you succeed?
- Is there anything else investors MUST know that I haven't asked about?
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 · 848 lines · 42 tokens per session scan A 554a2f1b4161
create is a command published in the GitHub repository dkorobtsov/pitch-deck (10 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 6,747 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.