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/EditorialOS/pinterest-marketing-strategistWrote 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/editorialos/pinterest-marketing-strategist/create)<a href="https://agentmods.dev/commands/editorialos/pinterest-marketing-strategist/create"><img src="https://agentmods.dev/badge/commands/editorialos/pinterest-marketing-strategist/create/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/editorialos/pinterest-marketing-strategist/create"><img src="https://agentmods.dev/badge/commands/editorialos/pinterest-marketing-strategist/create.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 | $0.00047 | $0.02946 |
| Opus 5 | $0.00023 | $0.01473 |
| Sonnet 5 | $0.00009 | $0.00589 |
| Haiku 4.5 | $0.00005 | $0.00295 |
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 10d 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create
One command. Composed pins out. Review, approve, post.
This is a production workflow, not a brainstorming tool. The output is a batch of pins where every element — title, description, image, board, keywords, posting time — is selected and matched. The human reviews the composed batch and decides what ships. Everything else is handled.
Trigger
Use when the user wants Pinterest pins created. Works with a specific topic, "next from queue," a product to promote, content to repurpose, or "this week's pins." Minimum input: a topic or "next."
Inputs
- Topic or "next" — what the pins are about. "Next" picks the first unposted topic from the pin queue in ~~docs. (Required)
- Batch size — optional. Default: 5 pins. Max recommended: 10.
- Boards — optional. Default: uses configured boards from /setup.
- Goal override — optional. Default: uses goal from /setup.
- Seasonal hook — optional. "Memorial Day," "back to school," "Q4 planning season."
Step 1 — Load Context
Use client-context skill. Show one-line status header.
🟢 Configured: load brand guide, audience, boards, pin history, learnings, image library inventory, and destination URLs from ~~docs. 🟡 Partial: load what exists, flag what's missing. ⚪ No client: ask for brand name, audience, boards, image source. State output will be directional.
Hard requirements before proceeding:
- Image library must have at least 1 usable image. If zero images exist anywhere (~~images or ~~docs images/), stop and tell the user: "No images found. Pinterest is a visual platform — add approved brand images to your Drive images/ folder or connect Cloudinary, then re-run."
- If no destination URLs are configured, flag it but proceed: "No destination URLs configured. Pins will drive awareness but not trackable traffic. Add landing pages and re-run /setup to enable traffic goals."
Step 2 — Check Pin History
Read pin-log.md from ~~docs (written by prior /track runs).
- What topics were covered in the last 14 days? Avoid exact repeats.
- What images were used in the last 10 pins? Don't reuse the same image.
- What angles performed best? Lean toward proven patterns.
- What angles underperformed? Note and avoid unless the underperformance had an identifiable cause (e.g., horizontal image, not the angle itself).
- Which boards are overdue for fresh pins? Prioritize underserved boards.
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.
- 10d ago First seen · 325 lines · 47 tokens per session scan A 2f462750c754
create is a command published in the GitHub repository EditorialOS/pinterest-marketing-strategist (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,946 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
install
Install a ComfyUI custom node pack.
cwb-relax
A command that searches for relaxing music in three styles: downtempo, acoustic folk, and nature ambience.
render-carousels
Render multi-slide carousels from HTML templates via Playwright.
dashboard
Build a shareable HTML dashboard of your hunt — funnel, status, categories, recruiter scores — from the tracker.
clean-check
Analyze code for cleanliness issues (unused code, comment quality, formatting, naming, complexity). Delegates to the code-cleanliness agent.
octo-brainstorm
"Start a creative thought partner brainstorming session".