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/launch-meta-campaign)<a href="https://agentmods.dev/commands/markifact/markifact-mcp/launch-meta-campaign"><img src="https://agentmods.dev/badge/commands/markifact/markifact-mcp/launch-meta-campaign/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/launch-meta-campaign"><img src="https://agentmods.dev/badge/commands/markifact/markifact-mcp/launch-meta-campaign.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 | $0.00036 | $0.01306 |
| Opus 5.5 | $0.00014 | $0.00522 |
| Sonnet 5.5 | $0.00007 | $0.00261 |
| Haiku 4.5 | $0.00004 | $0.00131 |
Grade A, and why
launch-meta-campaign 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Stand up a production-ready Meta campaign with one ad set and one or more ad variants in one flow. Always start paused.
Inputs to confirm (batch)
- Ad account name (substring) — required.
- Campaign objective —
OUTCOME_SALES,OUTCOME_LEADS,OUTCOME_TRAFFIC,OUTCOME_AWARENESS,OUTCOME_ENGAGEMENT,OUTCOME_APP_PROMOTION. Required. This cannot be changed later — picking wrong forces a full rebuild. - Conversion location (for Sales/Leads): website + pixel + event, or lead form, or messaging.
- Budget structure — campaign budget (CBO / Advantage Campaign Budget) or ad-set budget (ABO). Required. CBO is default-on for new campaigns. Pick before creating because switching later is messy.
- Daily budget — required.
- Targeting: location(s), age range, gender, languages, detailed interests/behaviors (or Advantage+ Audience).
- Placements: Advantage+ Placements (recommended) or manual. If manual, which platforms (FB, IG, Messenger, Audience Network) and which positions (feeds, stories, reels, etc.).
- Schedule: continuous or start/end dates.
- Ad format: single image, single video, carousel, catalog (DPA), flexible / dynamic creative.
- Creative inputs: image/video file IDs (if user attached) or URLs, primary text, headline, description, CTA, destination URL, Facebook Page ID, optional Instagram account ID.
Workflow
- Discover ops via
find_operations:meta_ads_select_accounts,meta_ads_create_campaign,meta_ads_create_adset,meta_ads_create_single_image_ad,meta_ads_create_single_video_ad,meta_ads_create_carousel_ad,meta_ads_create_catalog_ad,meta_ads_create_flexible_ad,meta_ads_search_targeting,meta_ads_list_account_pixels,meta_ads_list_custom_audiences. - Inspect with
get_operation_inputs. - Resolve account:
meta_ads_select_accountssubstring. - Resolve targeting if user gave interest/behavior names →
meta_ads_search_targetingto get IDs. - Resolve pixel for conversions →
meta_ads_list_account_pixels. - Create campaign (status=PAUSED) with chosen objective + CBO/ABO setting + budget if CBO.
- Create ad set under that campaign with: optimization goal (matches objective), conversion event, audience, placements, schedule, budget if ABO. Status=PAUSED.
- Create ad(s) — pick the right
meta_ads_create_*_adop for the format. Status=PAUSED. - Confirm to user with IDs + reminder to review and unpause.
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 · 71 lines · 36 tokens per session scan A dee051c0a296
launch-meta-campaign is a command published in the GitHub repository markifact/markifact-mcp (52 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 1,306 once invoked, about $0.0001 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.
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.
financial-model
Build a financial model or business case with projections.