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 elie222/atom-eve --skill ppc-assistgit clone --depth 1 https://github.com/elie222/atom-eveWrote 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/elie222/atom-eve/ppc-assist)<a href="https://agentmods.dev/skills/elie222/atom-eve/ppc-assist"><img src="https://agentmods.dev/badge/skills/elie222/atom-eve/ppc-assist/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/elie222/atom-eve/ppc-assist"><img src="https://agentmods.dev/badge/skills/elie222/atom-eve/ppc-assist.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 | $0.00034 | $0.00664 |
| Opus 5 | $0.00017 | $0.00332 |
| Sonnet 5 | $0.00007 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
ppc-assist 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPC Assist Workflow
Use the PPC Assist connection as the account's primary source of truth. The connection returns raw store, campaign, product, keyword, search-term, strategy, suggestion, audit, and bid-estimate facts. You do the judgment and writing.
Discovery
Before calling an operation, use connection_search for the relevant PPC Assist capability. Inspect the discovered tool names and input schemas, then call the qualified ppcassist__... tool.
Use explicit date ranges when dates are named. Use rolling period_days only when the user asks for a relative window or no exact dates are configured.
Store Selection
Start with list_stores when the target store is not already clear. If exactly one store is available, use it. If multiple stores are available and no target store is configured, stop and ask the user to choose one.
For an agency or multi-store view, use get_all_stores_overview for account-level prioritization, then drill into one selected store before making store-level recommendations.
Triage Loop
For a broad daily or weekly run, gather:
- store overview and account strategy
- products and product goals
- campaigns and campaign details for the highest-impact candidates
- keywords and search terms
- pending suggestions
- applied strategies, campaigns without strategy, and products without campaigns
- bid estimates when bid changes are under consideration
- activity, orders, listing details, and search query performance when product context matters
Run the audit operation for broad account-health checks or when the user asks for an audit. Treat audit output as evidence, not as an automatic decision.
Interpreting Metrics
Prioritize issues by impact, confidence, and reversibility.
- ACOS/TACOS drift: compare to configured targets and product lifecycle. Launch products may tolerate higher ACOS; mature products need stronger efficiency.
- Wasted spend: flag spend with no sales only when the spend is meaningful for that account and window.
- Search terms: separate non-converters, proven converters, and terms that need exact control or negatives.
- Campaign coverage: flag products without campaigns and campaigns without strategies when they conflict with the configured growth plan.
- Budget pressure: distinguish constrained proven campaigns from campaigns that should not receive more budget.
- Suggestions: review the evidence behind each suggestion before recommending validation or ignore.
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 · 57 lines · 34 tokens per session scan A d3a90fc61f10
ppc-assist is a skill published in the GitHub repository elie222/atom-eve (49 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 664 once invoked, about $0.0002 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
seo-audit
How to present the deterministic AI-SEO audit returned by auditpage. Use when reporting a page's readability and citation-readiness for AI answer engines (ChatGPT, Claude, Perplexity).
workspace
How to safely operate the sandboxed workspace. Use for any multi-step task involving files or shell commands.
research
Iterative, self-evaluating web research. Use when answering open-ended questions that require gathering and verifying information from multiple sources.
writing-quality
Writing-quality guardrails for any prose the agent drafts or edits: blog posts, page copy, Notion drafts, release notes, marketing text. Use this skill whenever writing or revising content meant for humans to read, to keep the prose natural, plain, and free of AI-sounding phrasing. Not needed for code, queries, or…
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this skill…
portable-text-serialization
Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown…