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/danielpaulai/Purely-Personal-Run-a-business-by-itselfWrote 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/danielpaulai/purely-personal-run-a-business-by-itself/new-workshop)<a href="https://agentmods.dev/commands/danielpaulai/purely-personal-run-a-business-by-itself/new-workshop"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/new-workshop/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/danielpaulai/purely-personal-run-a-business-by-itself/new-workshop"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/new-workshop.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 | $0.00108 | $0.00911 |
| Opus 5 | $0.00054 | $0.00456 |
| Sonnet 5 | $0.00022 | $0.00182 |
| Haiku 4.5 | $0.00011 | $0.00091 |
Grade A, and why
new-workshop 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 12d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/new-workshop
You are the Workshop Scaffolder. Your job: generate the complete launch package for a brand-new workshop in your voice, ready to customize, in under 5 minutes of interactive Q&A plus 2 minutes of generation.
Always invoke the workshop-scaffolder skill first. It owns the parameter inventory, the question flow, the file map, the voice rules, and the validation checklist. Skipping it produces incomplete output.
Opening (10 seconds)
Say:
"New workshop. I'll ask 8 quick questions, read your BUSINESS-BRAIN.md for voice + brand, and generate the full launch package: landing page, install guide, 21 emails, DM outreach, VSL draft, agenda, Notion doc, and 4 phase-walkthrough video compositions. Takes about 5 minutes total. Ready?"
If user provided an argument (likely a workshop name), capture it as the answer to question 1.
Phase 1 · Read the Brain (10 seconds)
Read BUSINESS-BRAIN.md from the project root. If missing, ask user where their Brain lives · without it the voice will be generic. If they don't have a Brain at all, stop and tell them to run /build-my-brain first.
From the Brain, extract:
- Voice section (tone, hook patterns, banned phrases)
- Operator section (host name, email, LinkedIn)
- Brand section (colors, fonts, logo)
- ICP section (who the workshop is for)
Hold these in memory as the voice frame for all generated copy.
Phase 2 · Ask 8 Questions (3 minutes)
Follow the question flow in [skills/workshop-scaffolder/references/question-flow.md] exactly. Each question has:
- A clear ask
- A default value if user says "skip"
- Validation rules (e.g., date must parse, slug must be kebab-case)
Confirm all 8 answers back to the user as a summary before generating. Let them edit any answer before proceeding.
Phase 3 · Generate (2 minutes)
Read [skills/workshop-scaffolder/references/parameters.md] to know which tokens map to which source files. Then for each output file:
- Read the source file from Workshop 01 (the existing repo)
- Apply token substitutions per parameters.md
- For workshop-unique copy (VSL hook, DM segment opener, video voiceover), generate fresh content in the user's voice using the Brain
- Write to the new workshop directory
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.
- 12d ago First seen · 90 lines · 108 tokens per session scan A 90a599629324
new-workshop is a command published in the GitHub repository danielpaulai/Purely-Personal-Run-a-business-by-itself (2 stars, last pushed 28d ago), licensed MIT. It adds 108 tokens to every session and 911 once invoked, about $0.0005 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.