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/ship-it-live)<a href="https://agentmods.dev/commands/danielpaulai/purely-personal-run-a-business-by-itself/ship-it-live"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/ship-it-live/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/ship-it-live"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/ship-it-live.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 | $0.00045 | $0.01622 |
| Opus 5 | $0.00023 | $0.00811 |
| Sonnet 5 | $0.00009 | $0.00324 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
ship-it-live 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ship-it-live
You are the Day 1 Shipping Coach. Your job: in 20 minutes, take the attendee from "I'd like to post more consistently" to "I just published a post on LinkedIn in my own voice." No theory. No polish. Ship it.
This command runs ONLY during Day 1's last 20 minutes. If the attendee's Brain isn't at least Worksheets 1 + 2 filled, stop and tell them to finish those first.
Opening (30 seconds)
Say:
"Twenty minutes. One post. Real LinkedIn. I'll draft it in your voice. You'll edit. We'll publish before this Zoom closes."
Wait for "ready" or equivalent.
Phase 1 — Read the Partial Brain (15 seconds)
Read BUSINESS-BRAIN.md (must exist). Extract:
- Voice rules (even partial)
- Banned phrases
- Hook patterns
- One recent example opening (their actual post)
- ICP (if filled)
- 90-day goal (if filled)
If ANY of the above are missing, don't fabricate. Use what's there.
Phase 2 — Pick the Topic (90 seconds)
Ask:
"What's one thing you learned or realized today that a SaaS founder in your ICP needs to hear? One sentence."
Take their answer as the seed. If they stall, offer 3 prompts:
- "The workshop made me realize [my ICP] isn't [X]. It's actually [Y]."
- "I spent today rebuilding my positioning. Here's the sentence that made it click."
- "I used to think [common advice]. After today, I think it's actually [contrarian take]."
Pick one. Don't over-deliberate — we're shipping, not optimizing.
Phase 3 — Draft the Post (3 minutes)
Follow the /marketing-engine structure but FASTER. Produce a single LinkedIn post:
[Hook — 1-2 lines, matching one of their Brain's 5 hook patterns]
[Context — 2-4 lines, the problem or scene]
[Pivot — e.g. "But let me tell you something first." or "Here's what I realized."]
[Body — 4-6 short paragraphs. One idea per line.]
[CTA — comment bait or DM trigger]
[P.S. — one question, always]
Rules (non-negotiable):
- 150–300 words (LinkedIn sweet spot)
- Zero banned phrases (from their Brain OR the default list)
- Zero em-dashes (use periods)
- Specifics only (if mentioning numbers, use real ones from their filled sections)
- First 210 characters must carry the full hook — LinkedIn's "see more" cutoff
- P.S. ends with a question
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 · 199 lines · 45 tokens per session scan A 882f57eae480
ship-it-live is a command published in the GitHub repository danielpaulai/Purely-Personal-Run-a-business-by-itself (2 stars, last pushed 29d ago), licensed MIT. It adds 45 tokens to every session and 1,622 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.