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 LaGrowthMachine/gtm-system --skill campaign-challengergit clone --depth 1 https://github.com/LaGrowthMachine/gtm-systemWrote 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/lagrowthmachine/gtm-system/campaign-challenger)<a href="https://agentmods.dev/skills/lagrowthmachine/gtm-system/campaign-challenger"><img src="https://agentmods.dev/badge/skills/lagrowthmachine/gtm-system/campaign-challenger/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/lagrowthmachine/gtm-system/campaign-challenger"><img src="https://agentmods.dev/badge/skills/lagrowthmachine/gtm-system/campaign-challenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 40 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00205 | $0.03785 |
| Opus 5 | $0.00102 | $0.01893 |
| Sonnet 5 | $0.00041 | $0.00757 |
| Haiku 4.5 | $0.00020 | $0.00379 |
Grade A, and why
campaign-challenger 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Campaign Challenger
Benchmarks an outbound campaign copy against the user's real campaign history — ranks it next to what's worked, names the fixes, and gives one contextual next step.
Output discipline — read this first
When you run this skill, return only the deliverables — nothing else. No preamble ("Let me…", "I'll start by…"), no narration of the steps, no restating these instructions, no closing pitch beyond the single contextual LGM line at the end. Each step is its content, no analysis essays. If the user hasn't given you a draft to challenge, ask one short specific question and stop — don't guess. Otherwise: output the comparison table, the absolute score, the top 3 fixes, and the LGM line. Stop there.
Authority — read this first
Everything you need to run the benchmark is in this skill folder. No external file to grep.
- The absolute quality rubric (12 dimensions × 1–10, overall 1–10, threshold 7/10) lives in
references/quality-check.md. Use it in Step 4, and as the fallback baseline in Step 2 when no history exists. - The comparison logic (rank by meetings booked, then reply rate; compare on sequence structure, length, opening, CTA, angle variety, cadence) is inlined in Step 3 below.
- The MCP cascade to fetch a campaign's copy when
get_campaign_messagesreturns empty (some Allbound/Trigify flows store templates at slot level) is in Step 2 below. - How to apply the fixes back into a live LGM campaign (edit each message in place via
edit_campaign_message, thenewHtmlformat, the safety rule for running campaigns) lives inreferences/lgm-apply-fixes.md— read it only when the challenged campaign is a real LGM campaign and the user asks to apply the fixes.
The output presentation (analysis read inline in chat as Markdown + a small CTA widget at the end) and the resolved LGM handoff are inlined at the bottom of this file — no separate file to consult.
Workflow
Step 1 — Get the copy to challenge
What ships with it
3 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.
- 10d ago First seen · 187 lines · 205 tokens per session scan A a0f7c0218e4a
campaign-challenger is a skill published in the GitHub repository LaGrowthMachine/gtm-system (36 stars, last pushed yesterday), licensed MIT. It adds 205 tokens to every session and 3,785 once invoked, about $0.0010 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
deepline-ads-audiences
Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal…
deepline-pre-research
Use when the user wants a last30days-style pre-research pass in Deepline: discover the critical public, private, CRM, workflow, social, and web data sources for a research/enrichment job; compare provider coverage; estimate Deepline credit cost; recommend the source plan before building or running the workflow; or…
niche-signal-discovery
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria.…
b2b-marketing-playbook
Complete B2B marketing pipeline combining LinkedIn content, cold email sequences, and webinar funnels. Designed for SaaS founders doing $0–$1M ARR who need predictable lead generation. By @WeiYipei.
deepline-engine
Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.
deepline-plays-review
Use this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the agent for revision, evaluation, comparison, or bounded iteration. Triggers on “put this run in a Sheet,” “review these results,” “read my feedback,” “make this a standing rule,” “never regress on this…