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 shinypebble/microsoft-ads-mcp --skill microsoft-ads-optimizergit clone --depth 1 https://github.com/shinypebble/microsoft-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/shinypebble/microsoft-ads-mcp/microsoft-ads-optimizer)<a href="https://agentmods.dev/skills/shinypebble/microsoft-ads-mcp/microsoft-ads-optimizer"><img src="https://agentmods.dev/badge/skills/shinypebble/microsoft-ads-mcp/microsoft-ads-optimizer/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/shinypebble/microsoft-ads-mcp/microsoft-ads-optimizer"><img src="https://agentmods.dev/badge/skills/shinypebble/microsoft-ads-mcp/microsoft-ads-optimizer.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 | $0.00026 | $0.04072 |
| Opus 5 | $0.00013 | $0.02036 |
| Sonnet 5 | $0.00005 | $0.00814 |
| Haiku 4.5 | $0.00003 | $0.00407 |
Grade A, and why
microsoft-ads-optimizer 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 8d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Advertising optimizer
A playbook for operating a single Microsoft Advertising (Bing Ads) account through the
microsoft-ads MCP server.
Start here
- Call
account_healthto confirm credentials and learn whether writes are enabled (read_only). Branch onauth_state/needs_interactive_auth: only run the interactive sign-in whenneeds_interactive_authis true (no_token/token_expired). Atoken_rejectedoraccount_inactivestate is not fixed by re-auth — re-consent can clobber a shared token; check the developer token / account binding instead. - Call
search_accountsto find the account/customer ids if they are not pre-configured. Useset_active_account(account_id)to switch which account subsequent calls hit, then re-confirm withaccount_healthbefore writing.
Finding tools (search + execute discovery)
The server runs in one of two modes; the rest of this playbook names tools by their real names, which work identically in both.
-
Full catalog (default,
TOOL_SEARCH=false) — every tool is listed directly. Call them by name as written below. -
Search + execute (
TOOL_SEARCH=true) — only a small set of always-visible core / getting-started tools is listed up front:account_health,search_accounts,get_campaigns,run_performance_report, and the auth tools (get_auth_url,complete_auth). Everything else (the rest of the reads, and all writes) is discovered on demand through two synthetic tools:search_tools(query)— BM25 search over tool names, descriptions, and parameters. Query in plain language for the capability you need, e.g.search_tools("add negative keywords")orsearch_tools("set location intent presence").call_tool(name, arguments)— invoke a discovered tool by name, passing its arguments as an object, e.g.call_tool("update_campaign", {"campaign_id": "123", "status": "Active"}).
Hidden tools keep their full typed schemas, so once
search_toolssurfaces one you get the same parameters documented here. The flow is: start from a pinned tool (usuallyaccount_health→get_campaigns), thensearch_toolsto locate the specific lever andcall_toolto run it.
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.
- 8d ago First seen · 224 lines · 26 tokens per session scan A 4faac2d2b106
microsoft-ads-optimizer is a skill published in the GitHub repository shinypebble/microsoft-ads-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 4,072 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…