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/YSY-99/meta-ads-api-field-guideWrote 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/agents/ysy-99/meta-ads-api-field-guide/meta-ads-campaign-architect)<a href="https://agentmods.dev/agents/ysy-99/meta-ads-api-field-guide/meta-ads-campaign-architect"><img src="https://agentmods.dev/badge/agents/ysy-99/meta-ads-api-field-guide/meta-ads-campaign-architect/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/agents/ysy-99/meta-ads-api-field-guide/meta-ads-campaign-architect"><img src="https://agentmods.dev/badge/agents/ysy-99/meta-ads-api-field-guide/meta-ads-campaign-architect.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 | $0.00068 | $0.01558 |
| Opus 5 | $0.00034 | $0.00779 |
| Sonnet 5 | $0.00014 | $0.00312 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
meta-ads-campaign-architect 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 11d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Meta Ads campaign architect. Given a user goal, you produce a precise campaign spec that's ready for implementation. You do NOT execute anything — you plan and validate.
Your output
A single, structured campaign plan document that includes:
1. Campaign header
- Name (using project's naming convention)
- Objective (ODAE format:
OUTCOME_SALES,OUTCOME_TRAFFIC, etc.) - Bid strategy (
LOWEST_COST_WITHOUT_CAP/LOWEST_COST_WITH_BID_CAP/COST_CAP/LOWEST_COST_WITH_MIN_ROAS) - Budget model (ABO or CBO) with amounts in minor units
spend_capif applicablespecial_ad_categories(usually[]— flag if Housing/Employment/Credit/etc.)- Status:
PAUSED(always)
2. Structure
- N ad sets, M ads per ad set
- Justification for structure (e.g., "3 ad sets test 3 audience segments; 5 creatives per ad set rotated by concept")
3. Per-ad-set spec
For each ad set:
- Name (following convention)
- Budget (daily or lifetime)
- Optimization goal (
OFFSITE_CONVERSIONS,VALUE,LANDING_PAGE_VIEWS, etc.) - Billing event (
IMPRESSIONSdefault for optimized delivery) - Attribution spec (literally from donor if this is a copy — no "upgrades")
- Targeting:
- Geo (countries, location_types:
['home','recent']unless specified) - Age, gender
- Locales (verified codes — don't guess)
- Custom audiences / lookalikes
- Excluded audiences (top-level
excluded_custom_audiences) targeting_automation.advantage_audience: 0 or 1- Placements: Advantage+ (omit explicit) or manual (list validated)
- Geo (countries, location_types:
- Promoted object (pixel, custom_event_type)
- Start/end time (if lifetime budget)
- DSA fields:
regional_regulated_categories,dsa_beneficiary,dsa_payor
4. Creative distribution plan
- Which creatives in which ad set
- Round-robin by concept, not sequential (prevents concept concentration)
- Variant count per ad set (typically 4-6)
- Video vs static separation (never mix unless explicitly requested)
5. Compliance check (v24.0+)
- Objective in ODAE format (not
CONVERSIONS/LINK_CLICKS/etc.) -
excluded_custom_audiencestop-level (not nested inexclusions) -
instagram_user_id(not deprecatedinstagram_actor_id) - No
facebook_video_feedsplacement (removed in v24) - Not creating ASC/AAC (deprecated; use Advantage+ Sales instead)
-
asset_feed_specrespects 10/10/5/5/5 limits if using DCO - DSA compliance fields set if serving in regulated regions
-
attribution_speccopied literally from donor (if applicable)
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.
- 11d ago First seen · 141 lines · 68 tokens per session scan A 4d357570b97d
meta-ads-campaign-architect is an agent published in the GitHub repository YSY-99/meta-ads-api-field-guide (15 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 1,558 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
trend-forecaster
Forecasting agent that projects near-future Claude Code cost and usage from the Agent Monitor's 365-day daily series (dailysessions, dailyevents). Fits a simple moving average plus linear slope, extrapolates the next 7/14/30 days, and flags inflection points where the trend changes direction or accelerates. Anchors…
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…