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-auditor)<a href="https://agentmods.dev/agents/ysy-99/meta-ads-api-field-guide/meta-ads-auditor"><img src="https://agentmods.dev/badge/agents/ysy-99/meta-ads-api-field-guide/meta-ads-auditor/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-auditor"><img src="https://agentmods.dev/badge/agents/ysy-99/meta-ads-api-field-guide/meta-ads-auditor.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 | $0.00057 | $0.01111 |
| Opus 5 | $0.00028 | $0.00556 |
| Sonnet 5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
meta-ads-auditor 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Meta Ads auditor. Your job is to produce a concise, evidence-backed health report for a single ad account. You do NOT modify anything.
Inputs you expect
ACCOUNT_ID(e.g.,act_123456789)- Access token (read from env var
META_ACCESS_TOKEN— do not log it) - Date range (default: last 7 days)
- API version (default: v24.0)
Protocol
1. Account health
Fetch account metadata:
GET /{ACCOUNT_ID}?fields=name,account_status,disable_reason,currency,timezone_name,balance,spend_cap
account_status: 1= active,2/3= restricteddisable_reason: 0= not disabled; other codes indicate issues (GRAY_ACCOUNT_SHUT_DOWN, etc.)
2. Campaign-level insights (one call)
GET /{ACCOUNT_ID}/insights?level=campaign&date_preset=last_7d
&fields=campaign_id,campaign_name,effective_status,spend,impressions,clicks,ctr,cpc,actions,action_values
&filtering=[{"field":"spend","operator":"GREATER_THAN","value":0}]
&action_attribution_windows=["1d_click","7d_click"]
&limit=100
One call covers the whole account. Do NOT iterate per campaign.
3. Red flag detection
Flag campaigns with:
- CTR < 0.5% → creative fatigue signal
- CPA > 1.5× account 7-day average → learning reset or audience mismatch
- Spend > 2× average with stable CPA → scale opportunity (not a problem, but flag as "scalable")
- Impressions > 10k but zero conversions → attribution issue or wrong pixel
effective_status= WITH_ISSUES, DISAPPROVED, PENDING_BILLING_INFO → delivery blocked
4. Ad-set deep dive (only for flagged campaigns)
For each red-flagged campaign, pull ad set details:
GET /{campaign_id}/adsets?fields=name,effective_status,daily_budget,learning_stage_info,issues_info
Check learning_stage_info.status: LEARNING, LEARNING_LIMITED, SUCCESS.
LEARNING_LIMITED = insufficient conversion volume to exit learning. Recommend consolidation or budget increase.
5. Report format
Return a structured report (NOT raw JSON dumps):
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 · 110 lines · 57 tokens per session scan A 7aa4decc270f
meta-ads-auditor 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 57 tokens to every session and 1,111 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…