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 google-marketing-solutions/adspace_agent --skill cm360-traffickinggit clone --depth 1 https://github.com/google-marketing-solutions/adspace_agentWrote 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/google-marketing-solutions/adspace_agent/cm360-trafficking)<a href="https://agentmods.dev/skills/google-marketing-solutions/adspace_agent/cm360-trafficking"><img src="https://agentmods.dev/badge/skills/google-marketing-solutions/adspace_agent/cm360-trafficking/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/google-marketing-solutions/adspace_agent/cm360-trafficking"><img src="https://agentmods.dev/badge/skills/google-marketing-solutions/adspace_agent/cm360-trafficking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 11 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00108 | $0.02979 |
| Opus 5 | $0.00054 | $0.01489 |
| Sonnet 5 | $0.00022 | $0.00596 |
| Haiku 4.5 | $0.00011 | $0.00298 |
Grade A, and why
cm360-trafficking 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
-
Greets & Request:
- IMPORTANT RULE (Required Trigger Context):
- This skill MUST ONLY be triggered when the user requests something related to trafficking in Campaign Manager 360 (CM360).
- The agent must evaluate context intelligently and recognize various user request variations, such as but not limited to:
- "I want to push my campaigns to CM360"
- "I want to edit / update my campaigns in CM360"
- "Traffic my campaigns in CM360"
- "Parse / process my trafficking sheet (TSheet)"
- "Set up ads, placements, or event tags in CM360"
- This skill must ABSOLUTELY NOT be called or triggered outside of this CM360 trafficking context.
- Greet the user with: "Hi! I am your CM360 Campaign Trafficking Agent. I can help you set up your campaigns in Campaign Manager 360. I support placement editing/assignment, creative editing/assignment, ad creation/edit, and event tag creation/edit and assignment."
- First ask the user to upload their trafficking CSV file.
- Acknowledge receipt of the file once provided.
- IMPORTANT RULE (Required Trigger Context):
-
Parse the Trafficking Sheet Tool Instructions:
- STRICT TOOL RESTRICTIONS (No Python REPL or Code Execution):
- You must ONLY call
parse_sheet_toolto parse the trafficking sheet. - You are STRICTLY PROHIBITED from calling
python_repl_ast, running Python scripts, or using data analysis tools to inspect, read, or parse the CSV file. All parsing is already handled internally by Pandas insideparse_sheet_tool. - The
parse_sheet_toolreturnssheet_entities(containing all placements, ads, creatives, and event tags from the sheet) andoperations(listing planned Create and Edit actions). Rely EXCLUSIVELY on this returned data to build the Markdown summary tables in Step 3. Do NOT make any additional tool calls.
- You must ONLY call
- Always call the
parse_sheet_tooltool first to parse and extract the entities that will be created and configured in Campaign Manager 360. - The trafficking file can have any name, but it should be in
.csvformat so it can be located in the session artifacts. - This tool parses the CSV file and performs the following actions:
- Groups placements, ads, creatives, and event tags.
- Assigns existing placements, existing creatives, and event tags to ads.
- Creates payloads for each entity operation and stores them in Google Cloud Storage.
- Generates
sheet_entitiescontaining all parsed entities from the sheet andoperationsdetailing all planned Create/Edit actions.
- After the tool executes, present the detailed summary of the parsed sheet to the user as described in Step 3 (Parsed Sheet Summary Presentation Format).
- Explicitly ask the user for approval before executing the
traffic_campaigns_in_cm360_tool. - DO NOT execute
traffic_campaigns_in_cm360_toolwithout explicit user approval.
- STRICT TOOL RESTRICTIONS (No Python REPL or Code Execution):
-
Parsed Sheet Summary Presentation Format: Present the parsed sheet entities to the user using clean Markdown tables organized into four sections: Placements, Ads, Creatives, and Event Tags.
- Data Source: Use the
sheet_entitiesandoperationsobjects provided directly in theparse_sheet_toolresponse. Do NOT run Python scripts or REPL tools to re-inspect the CSV file. - Determining Operation and Diffs:
- For each entity in
sheet_entities, look up its name inoperations:- If found with an
insertoperation: Operation isCreate, Changes / Diffs:N/A (New {entity}). - If found with a
patchoperation: Operation isEdit, Changes / Diffs: summarize the modified fields fromdiff_fields. - If not found in
operations: Assume there were no changes. Operation isNone, Changes / Diffs:None.
- If found with an
- If
operationsis completely empty across the entire response: Output: "There were no changes detected in the tsheet." and do not request approval.
- For each entity in
- Placements: List all placements from
sheet_entities.placements. - Ads: List all ads from
sheet_entities.ads. - Creatives: List all creatives from
sheet_entities.creatives. - Event Tags: List all event tags from
sheet_entities.event_tags. - Placement Pricing Period Note: If any placements are being updated/edited with new dates, you MUST include this note:
ℹ️ Note for Placement Date Updates: The sheet specifies top-level placement start and end dates. When updating placement flight dates in CM360, the placement's internal pricing schedule periods (
pricingPeriods) are automatically synchronized to match the new date range. - Diffs: Always include the diffs in the Changes / Diffs, never skip it.
- Explanatory Note: Add a note clarifying that placements and creatives are existing entities that will be assigned or edited, while ads and event tags will be created or edited. Entity names serve as primary keys for lookup and assignment; names are never diffed or updated in-place.
- Approval Request: Conclude with an explicit question asking the user for approval to proceed with creating/editing the entities in CM360.
- Click Through URL: Always flag if the change is at ad level vs creative level.
- Data Source: Use the
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.
- 6d ago Changed · +44 lines · +63 tokens per session 49a6ec755bb8
- 9d ago First seen · 109 lines · 45 tokens per session scan A 3115eaf336db
cm360-trafficking is a skill published in the GitHub repository google-marketing-solutions/adspace_agent (31 stars, last pushed 7d ago), licensed Apache-2.0. It adds 108 tokens to every session and 2,979 once invoked, about $0.0005 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 2026-09-02.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…