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/stepolan/marketing-repo-template/setupgit clone --depth 1 https://github.com/stepolan/marketing-repo-templateWrote 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/stepolan/marketing-repo-template/setup)<a href="https://agentmods.dev/commands/stepolan/marketing-repo-template/setup"><img src="https://agentmods.dev/badge/commands/stepolan/marketing-repo-template/setup.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 | $0.00012 | $0.00782 |
| Opus 5 | $0.00006 | $0.00391 |
| Sonnet 5 | $0.00002 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
setup 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walk the user through initial repo setup. This replaces the fictional Summit Fuel company and placeholder authors with their real company and team.
Execute the following steps interactively — ask questions and wait for answers before proceeding.
Step 1: Gather information
Ask the user for:
- Company name — What is your company called?
- One-line company description — What does the company do? (e.g. "a sports nutrition company for endurance athletes")
- Authors — Who will be writing content? For each author, ask:
- Name (first name or handle they publish under)
- Title (e.g. "Co-Founder and CEO", "Head of Marketing")
- One-sentence bio
Wait for all answers before proceeding.
Step 2: Replace the company
Find and replace across the entire repo:
- "Summit Fuel" → their company name
- "a sports nutrition company for endurance athletes" → their company description (in voice-guidelines.md and author-bios.md)
- Update
brand/voice-guidelines.md— keep the structure and rules, replace Summit Fuel references - Update
CLAUDE.md— replace any Summit Fuel references
Step 3: Set up authors
For each author the user listed:
- Rename an existing author directory. Map the first author to
caesar/, the second tozira/. If they have more than two authors, create new directories following the same structure. - Update
brand/author-bios.mdwith the real names, titles, and bios - Update the voice profile at
authors/<name>/voice/voice-profile.md— replace the fictional author name but keep the template structure and "Status: Template — customize for your author" note. The user will run/extract-voicenext to fill it in properly. - Create the full directory structure for each author:
authors/<name>/samples/with the README.md explaining what to put thereauthors/<name>/drafts/linkedin/authors/<name>/posted/linkedin/authors/<name>/ideas/authors/<name>/voice/voice-profile.md
If there are fewer than two authors, delete the unused author directory entirely.
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.
- 5d ago First seen · 78 lines · 12 tokens per session scan A 6f77a8e4c00c
setup is a command published in the GitHub repository stepolan/marketing-repo-template (2 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 782 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
repurpose
Fan a QA'd long-form piece (blog, research, weekly report) down into 6 channel-native formats — X thread, X singles, LinkedIn article, newsletter snippet, and pull-quote cards. Every output is canon-checked and staged for review.
blog-assets
Build HTML templates for each visual placeholder in a blog article and batch-export them as 1200x675 PNGs at 2x. Fourth step in the blog production pipeline.
blog-pipeline
Reference document showing the full Blog Engine flow with human approval gates. This is not an executable command — it's a map of how blog commands connect.
compliance-check
Jurisdiction-aware content compliance validation. Scans copy for regulatory violations, banned claims, missing disclaimers, and financial promotion language.
content-pipeline
Reference document showing the full Content Engine flow with human approval gates. This is not an executable command — it's a map of how content commands connect.
content-week
Batch-produce all visual assets for the week's approved content. Builds banners, renders videos, exports PNGs. No manual steps after this — everything comes out ready to post.