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 octavehq/lfgtm --skill ads-resonancegit clone --depth 1 https://github.com/octavehq/lfgtmWrote 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/octavehq/lfgtm/ads-resonance)<a href="https://agentmods.dev/skills/octavehq/lfgtm/ads-resonance"><img src="https://agentmods.dev/badge/skills/octavehq/lfgtm/ads-resonance/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/octavehq/lfgtm/ads-resonance"><img src="https://agentmods.dev/badge/skills/octavehq/lfgtm/ads-resonance.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 | $0.00136 | $0.10214 |
| Opus 5 | $0.00068 | $0.05107 |
| Sonnet 5 | $0.00027 | $0.02043 |
| Haiku 4.5 | $0.00014 | $0.01021 |
Grade B, and why
ads-resonance scanned grade B with 2 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 12d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**Critical principle**: never tell the user "I can pull your data" without running a smoke test first. A path that *looks* available (the MCP tool exists, the dataset exists, the dev token is set) can still fail at query Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **Direct API** (curl/Python against the Google Ads API, no MCP) — when the user has an approved developer token but no MCP installed How it starts
The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octave Ads Resonance Loop — Performance → Library Intelligence
Turn ad performance data into GTM intelligence: pull performance from whichever source is available, map winners and losers back to the source cards that produced them, recommend library updates, brief the sales team on what language the market responds to, and write falsifiable prediction cards so the loop builds a verifiable track record over time.
Companion skill: /octave:ads builds the campaigns this loop analyzes. Campaigns generated there persist source cards to ~/.octave/source_cards/ (the data contract is defined in /octave:ads Step 2G and source-cards.template.json), which unlocks this loop's strongest analysis path. The loop also works on campaigns created outside /octave:ads via reverse-inference.
MCP Server: Library updates (Step 3) require the Octave MCP server. Look for available MCP tools that match the Octave tool names (e.g., update_entity, update_motion_playbook). The MCP server prefix varies by workspace. If multiple Octave-like MCP servers are available and you're unsure which to use, ask the user which workspace to target.
Output principles: every output follows the shared principles — presentation principles for visuals (the HTML dashboard, tables), editorial rules for text (the brief, recommendations, prediction cards).
Review pass: before final delivery, run the preflight from protocol.md (em dashes, leaked internals, placeholders) over the text output. Any HTML dashboard generated in Step 6 takes the full protocol as a mandatory gate: it is not opened or delivered until the combined scorecard has printed.
Step 1: Detect Performance Data Source
Performance data can come from four places, in order of preference:
- MCP (live Google Ads / Meta / LinkedIn API via an installed MCP server) — real-time, but most likely to fail at runtime
- BigQuery Data Transfer Service (~24h delayed managed pipeline) — the recommended default for read-only resonance analysis, no developer token approval required
- Direct API (curl/Python against the Google Ads API, no MCP) — when the user has an approved developer token but no MCP installed
- Manual (paste CSV / screenshot / verbal) — last resort
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 565 lines · 136 tokens per session scan B 63993798599b
ads-resonance is a skill published in the GitHub repository octavehq/lfgtm (11 stars, last pushed 21d ago), licensed MIT. It adds 136 tokens to every session and 10,214 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (subtle steering, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…