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.
npx skills add amekala/ads-mcp --skill adspirer-setupgit clone --depth 1 https://github.com/amekala/ads-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/skills/amekala/ads-mcp/adspirer-setup)<a href="https://agentmods.dev/skills/amekala/ads-mcp/adspirer-setup"><img src="https://agentmods.dev/badge/skills/amekala/ads-mcp/adspirer-setup/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/skills/amekala/ads-mcp/adspirer-setup"><img src="https://agentmods.dev/badge/skills/amekala/ads-mcp/adspirer-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 128 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00052 | $0.01437 |
| Opus 5 | $0.00026 | $0.00718 |
| Sonnet 5 | $0.00010 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
adspirer-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the full brand workspace setup. Follow these steps in order:
Step 1: Connect to Adspirer
Call get_connections_status directly.
- If it works: continue to step 2.
- If the MCP server is not found: tell the user:
"The Adspirer MCP server isn't connected. Run:
codex mcp add adspirer --url https://mcp.adspirer.com/mcpThen restart Codex, authenticate via/mcp, and run$adspirer-setupagain." - If OAuth is triggered: tell the user a browser window is opening for authentication. Wait for them to confirm, then retry.
- If no platforms are connected: tell the user to connect ad accounts at https://adspirer.ai/connections, then run setup again.
Step 2: Scan local folder
Search for brand documentation files: **/*.md, **/*.txt, **/*.csv, **/*.yaml, **/*.json, **/*.pdf
Read all discovered files. Extract:
- Brand name and industry
- Products/services
- Target audience descriptions
- Brand voice and tone indicators
- Competitor mentions
- Budget information
- KPI targets or performance goals
- Previous campaign strategies or results
If the folder is empty, that's fine — we'll build context from Adspirer data alone.
Step 3: Pull live campaign data
Call these Adspirer MCP tools (in parallel where possible):
get_connections_status— which platforms are connectedget_business_profile— saved brand profilelist_campaigns— existing campaigns across all platformsget_campaign_performance(lookback_days: 30) — Google Ads performanceget_linkedin_campaign_performance(lookback_days: 30) — LinkedIn performanceget_meta_campaign_performance(lookback_days: 30) — Meta performanceget_benchmark_context— industry benchmarks
If any tool errors (platform not connected), skip it and note the gap.
Step 4: Create AGENTS.md
Generate AGENTS.md at the project root. Combine local files + Adspirer data:
# [Brand Name] — Paid Media Workspace
## Brand Overview
[From docs + Adspirer: what they sell, who they sell to, industry, company size]
## Brand Voice
[From docs: tone, language style, prohibited words, preferred phrases]
[If not found: "No brand voice docs found — add guidelines to this folder to improve ad copy quality"]
## Target Audiences
[From docs + Adspirer campaign targeting data]
[List each audience with platform-specific targeting parameters if available]
## Active Platforms
[From get_connections_status]
- Google Ads: [connected/not connected] — [X active campaigns]
- Meta Ads: [connected/not connected] — [X active campaigns]
- LinkedIn Ads: [connected/not connected] — [X active campaigns]
- TikTok Ads: [connected/not connected] — [X active campaigns]
## Budget & Guardrails
[From docs if available, otherwise from Adspirer campaign data]
- Monthly total: [amount or "Not specified — ask user"]
- Platform allocation: [percentages or "Based on current spend: ..."]
- Max CPC: [if specified]
- Target CPA: [if specified]
- Min ROAS: [if specified]
## KPI Targets
[From docs if available]
- Primary goal: [leads/sales/awareness/traffic]
- Target metrics: [CTR, CPA, ROAS targets]
## Current Performance Snapshot
[From get_campaign_performance — most recent data]
| Platform | Campaigns | Monthly Spend | CTR | CPA | ROAS |
|----------|-----------|---------------|-----|-----|------|
| ... | ... | ... | ... | ... | ... |
## Key Findings from Existing Campaigns
[From analyze_search_terms + performance data]
- Top performing keywords: ...
- Top performing campaigns: ...
- Wasted spend areas: ...
- Recommendations: ...
## Competitors
[From docs if available]
## Seasonality
[From docs if available]
## Notes
[Anything else relevant found in docs]
[Gaps: "No brand voice guide found", "No budget specified", etc.]
[Known constraints:
- Conversion action primary/secondary setup is configured manually in Google Ads UI (not via Adspirer MCP)
- Campaign creation should be considered complete only after post-create verification of ads, keywords, and extensions]
## Strategy
Active strategy directives are maintained in `STRATEGY.md`. All skills and agents read
that file before campaign creation, keyword research, and ad copy generation.
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 · 183 lines · 52 tokens per session scan A 29b5798df509
adspirer-setup is a skill published in the GitHub repository amekala/ads-mcp (89 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 1,437 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 skills, from other repositories
adspirer-ads-agent
Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 100+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
_mureo-shared
Skill "_mureo-shared" from logly/mureo, covering mureo shared patterns, installation, setup, claude code (recommended) and manual configuration.
_mureo-strategy
Strategy Context: Manage business strategy files (STRATEGY.md, STATE.json) for strategy-driven ad operations.
daily-check
Run a daily health check on all configured ad accounts (Google Ads, Meta Ads, Amazon Ads, TikTok Ads, Search Console, GA4, and any configured plugin platform). Use when the user asks for a daily review, health check, status update, anomaly detection, or 'how are my campaigns doing today'. Reads STRATEGY.md and…
_mureo-google-ads
Google Ads: Manage campaigns, ad groups, ads, keywords, budgets, and performance analysis.