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.
git clone --depth 1 https://github.com/navraj007in/architecture-cowork-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/commands/navraj007in/architecture-cowork-plugin/pitch-deck)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/pitch-deck"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/pitch-deck/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/commands/navraj007in/architecture-cowork-plugin/pitch-deck"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/pitch-deck.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 | $0.00021 | $0.02022 |
| Opus 5 | $0.00010 | $0.01011 |
| Sonnet 5 | $0.00004 | $0.00404 |
| Haiku 4.5 | $0.00002 | $0.00202 |
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 11d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:pitch-deck
Trigger
/architect:pitch-deck
Purpose
Generate a comprehensive, investor-ready pitch deck with web-verified market data. Produces both a markdown document and a PowerPoint file. Builds on all prior ideation outputs for maximum depth and accuracy.
Workflow
Step 1: Gather Context
Read in this order (do NOT ask the user — use what's available):
architecture-output/_state.json— read first if it exists; useproject,personas,market_research,mvp_scope,top_risks,tech_stack,componentsdirectly — these cover slides 2, 4, 5, 6, 7, 9, 10, 14 without needing intent.json or SDLintent.json— only if_state.json.projectis absent; extract name, vision, target users, core features, business constraints- SDL — only if
_state.json.componentsis absent; checksolution.sdl.yamlfirst; if absent, readsdl/README.mdthen the relevant module files. Grep forproduct:block (screens, coreFlows) andcomponents:block only — do NOT read the full file architecture-output/problem-validation.md— problem statement, evidence (read in full, typically small)architecture-output/cost-estimate.md— infrastructure and development costs for Slides 13-14 (read in full, typically small)architecture-output/deep-research.md— only if_state.json.market_researchis absent; if reading, Grep for "Market Sizing" and "Competitor Landscape" sections only. USE this data directly instead of re-researching.architecture-output/user-personas.md— only if_state.json.personasis absent; if reading, Grep for persona names and pain points onlyarchitecture-output/mvp-scope.md— only if_state.json.mvp_scopeis absent; if reading, Grep for "Must Have" section only
If _state.json.market_research and deep-research.md both do NOT exist, use WebSearch to research market data, competitors, and pricing. Tag numbers as [Verified] or [Estimated].
Step 2: Generate All 15 Slides
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.
- 11d ago First seen · 181 lines · 21 tokens per session scan A cf4f489c2d0e
pitch-deck is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 2,022 once invoked, about $0.0001 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
video
WATCH a video and return a structured VISUAL breakdown (not just a transcript) with Antigravity (agy / Gemini 3.x, natively multimodal in video). Scene-by-scene segments with timestamps, on-screen text/OCR (slides, charts, UI, captions), key visual events, and a summary. For screencasts, tutorials, presentations…
brand-generate
Generate an on-brand document from a saved Brand Profile.
add
Add a second payment provider alongside an existing integration, without touching the one already running.
search-flights
Search award flight availability across airlines.
vibe
Set session mood for TTS voice.
render-video
Convert an existing HTML slide deck or magazine to an MP4 via Hyperframes.