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/markifact/markifact-mcpWrote 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/markifact/markifact-mcp/rotate-creative)<a href="https://agentmods.dev/commands/markifact/markifact-mcp/rotate-creative"><img src="https://agentmods.dev/badge/commands/markifact/markifact-mcp/rotate-creative/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/markifact/markifact-mcp/rotate-creative"><img src="https://agentmods.dev/badge/commands/markifact/markifact-mcp/rotate-creative.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 | $0.00053 | $0.01642 |
| Opus 5.5 | $0.00021 | $0.00657 |
| Sonnet 5.5 | $0.00011 | $0.00328 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
rotate-creative 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Identify creative that's stopped performing, pause it, and ship variants. Preserve learning where possible. Always start new ads paused for review.
Inputs to confirm (batch)
- Account name (substring) — required.
- Platform — Meta or Google Ads (or both, if user says "all my ads") — required.
- Scope — campaign / ad set / ad group, or "all active" — required.
- Lookback window — default 30 days.
- Fatigue thresholds — defaults below; allow override:
- Meta: frequency > 3.5 AND CTR has dropped > 25% vs the prior period of equal length.
- Google: impressions stagnant or down > 20% WoW with CTR drop > 20%, OR RSA ad strength
Poor/Average.
- Minimum sample size before pausing — default ≥ 100 clicks AND ≥ 7 days of data. Refuse to pause anything below this.
- Variant strategy —
tweak(small copy/headline change),angle(new hook/benefit), orformat(e.g. image → video). Defaultangle. - How many variants per fatigued ad — default 2.
Workflow
Meta path
- Discover ops:
meta_ads_select_accounts,meta_ads_list_ads,meta_ads_get_report,meta_ads_list_report_fields,meta_ads_update_ad_status,meta_ads_duplicate_ad,meta_ads_get_ad_creative,meta_ads_create_ad_creative,meta_ads_replace_ad_creative,meta_ads_create_single_image_ad/_carousel_ad/_video_ad/_flexible_ad. - Inspect.
- Resolve account (substring).
- Pull ad-level report for the scope, current period vs prior period of equal length. Required fields: spend, impressions, clicks, CTR, conversions, frequency, ad_id, ad_name, adset_id, campaign_id.
- Apply thresholds → list of fatigued ads. Drop anything under the sample-size floor.
- For each fatigued ad, build a variant:
tweak→meta_ads_get_ad_creative→ modify primary text / headline →meta_ads_create_ad_creative→meta_ads_duplicate_ad(or create a fresh ad in the same ad set with the new creative) — start PAUSED.angle→ generate a new creative concept (different hook, benefit, or pain point) → usemeta_ads_create_single_image_ador_video_ad(etc.) withstatus=PAUSEDin the same ad set.format→ call the matching format's create op with the new asset.
- Show user a preview: each fatigued ad → its proposed variant(s), reasoning. Wait for approval.
- Execute:
a. Create the variants (PAUSED).
b. Pause the originals via
meta_ads_update_ad_status. - Confirm counts.
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.
- 1mo ago First seen · 99 lines · 53 tokens per session scan A 6b315036f533
rotate-creative is a command published in the GitHub repository markifact/markifact-mcp (52 stars, last pushed 16d ago), licensed MIT. It adds 53 tokens to every session and 1,642 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
change-plan
Create a comprehensive change management plan for a transformation initiative.
ma-strategy
Develop M&A strategy including target screening, synergy analysis, or integration planning.
financial-model
Build a financial model or business case with projections.
market-entry
Develop a market entry strategy for a new market, geography, or segment.
benchmark
Benchmark a company or function against peers and industry standards.
competitor-profile
Build a detailed profile of a specific competitor.